Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

The Intrinsic Dimension of Prompts in Internal Representations of Large Language Models

Karthik Viswanathan, Yuri Gardinazzi, Giada Panerai, Alberto Cazzaniga +1 more

Published

Jan 17, 2025

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

35% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Aug 21, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
0/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension. Viewing transformers as mean-field particle systems, we estimate the intrinsic dimension of the empirical measure at each layer and demonstrate that it correlates with next-token uncertainty. Across models and intrinsic dimension estimators, we find that intrinsic dimension peaks in early to middle layers and increases under syntactic and semantic disruption (by shuffling tokens), and that it is strongly correlated with average surprisal, with a simple analysis linking logits geometry to entropy via softmax. As a case study in practical interpretability and safety, we train a linear probe on the per-layer intrinsic dimension profile to distinguish malicious from benign prompts before generation. This probe achieves accuracy of 90 to 95\% in different datasets, outperforming widely used guardrails such as Llama Guard and Shield Gemma. We further compare against linear probes built from layerwise entropy derived via the Tuned Lens and find that the intrinsic dimension-based probe is competitive and complementary, offering a compact, interpretable signal distributed across layers. Our findings suggest that prompt-level geometry provides actionable signals for monitoring and controlling LLM behavior, and offers a bridge between mechanistic insights and practical safety tools.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension."

Quality Controls

missing

Not reported

No explicit QC controls found.

"We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension."

Reported Metrics

partial

Accuracy

Useful for evaluation criteria comparison.

"This probe achieves accuracy of 90 to 95\% in different datasets, outperforming widely used guardrails such as Llama Guard and Shield Gemma."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

accuracy
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • We study the geometry of token representations at the prompt level in large language models through the lens of intrinsic dimension.
  • Viewing transformers as mean-field particle systems, we estimate the intrinsic dimension of the empirical measure at each layer and demonstrate that it correlates with next-token uncertainty.
  • Across models and intrinsic dimension estimators, we find that intrinsic dimension peaks in early to middle layers and increases under syntactic and semantic disruption (by shuffling tokens), and that it is strongly correlated with average surprisal, with a simple analysis linking logits geometry to entropy via softmax.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Accuracy

Contribution summary

  • As a case study in practical interpretability and safety, we train a linear probe on the per-layer intrinsic dimension profile to distinguish malicious from benign prompts before generation.
  • This probe achieves accuracy of 90 to 95\% in different datasets, outperforming widely used guardrails such as Llama Guard and Shield Gemma.
  • Our findings suggest that prompt-level geometry provides actionable signals for monitoring and controlling LLM behavior, and offers a bridge between mechanistic insights and practical safety tools.

Why it matters for eval

  • As a case study in practical interpretability and safety, we train a linear probe on the per-layer intrinsic dimension profile to distinguish malicious from benign prompts before generation.
  • Our findings suggest that prompt-level geometry provides actionable signals for monitoring and controlling LLM behavior, and offers a bridge between mechanistic insights and practical safety tools.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: accuracy