#refusal

1 articles

01 ·Paper Deep-Dives·★ MEMBER·PAPER·9 min read Paper Explained: Refusal in Language Models Is Mediated by a Single Direction — saying "no" lives on one line inside the model When chat models turn down harmful requests, that behavior is carried by a single direction in the residual stream. This walkthrough reads the paper as an interpretability result: how a difference of mean activations finds the direction, why removing it stops refusal, and why adding it makes models refuse harmless requests across 13 models.