Refusal Vector

Creator
Creator
Seonglae Cho
Created
Created
2025 Jan 26 18:19
Editor
Edited
Edited
2025 Jul 24 10:50
Refs
Refs

Refusal Feature

Refusal Vector Usages
 
 
 
 
Misalignment is also expressed as a linear direction in activation space like the
Refusal Vector
, so it can be interpreted through rank-1 LoRA adapters. Emergent Misalignment converges to a single linear direction in activation space. This result is similar to how the
Refusal Vector
is a single direction. Furthermore, using the direction extracted from one fine-tune, misalignment was suppressed even in completely different datasets and larger LoRA configurations. Using just a rank-1 LoRA adapter, they induced 11% EM while maintaining over 99% coherence.
Further research is needed to directly compare the EM direction vs. refusal direction in activation space to understand their similarity and relationships at the circuit level.

LLMs Encode Harmfulness and Refusal Separately

The final token of user instructions (tinst) primarily encodes harmfulness, while the token after the system prompt (tpost-inst) mainly encodes whether to refuse
 

Recommendations