A proof-of-concept showing that logit lens and sparse autoencoders can partially recover a non-verbalized single-token secret from a fine-tuned language model, with an external LLM guessing from hints as the strongest baseline.
Eliciting latent knowledge: How to tell if your eyes deceive you, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards eliciting latent knowledge from LLMs with mechanistic interpretability
A proof-of-concept showing that logit lens and sparse autoencoders can partially recover a non-verbalized single-token secret from a fine-tuned language model, with an external LLM guessing from hints as the strongest baseline.