LatentQA: Teaching LLMs to Decode Activations Into Natural Language
Alexander Pan, Lijie Chen, Jacob Steinhardt · Dec 11, 2024 · Citations: 0
How to use this page
Low trustUse this as background context only. Do not make protocol decisions from this page alone.
Best use
Background context only
What to verify
Read the full paper before copying any benchmark, metric, or protocol choices.
Evidence quality
Low
Derived from extracted protocol signals and abstract evidence.
Abstract
Top-down transparency typically analyzes language model activations using probes with scalar or single-token outputs, limiting the range of behaviors that can be captured. To alleviate this issue, we develop a more expressive probe that can directly output natural language, performing LatentQA: the task of answering open-ended questions about activations. A key difficulty in developing such a probe is collecting a dataset mapping activations to natural-language descriptions. In response, we propose an approach for generating a dataset of activations and associated question-answer pairs and develop a fine-tuning method for training a decoder LLM on this dataset. We then validate our decoder's fidelity by assessing its ability to read and control model activations. First, we evaluate the decoder on a number of supervised reading tasks with a known answer, such as uncovering hidden system prompts and relational knowledge extraction, and observe that it outperforms competitive probing baselines. Second, we demonstrate that the decoder is precise enough to steer the target model to exhibit behaviors unseen during training. Finally, we show that LatentQA scales well with increasing dataset and model size.