head-selection

Tag

Cards List
#head-selection

LocUS: Head Selection and Subspace Projection for Targeted Activation Steering

arXiv cs.CL ↗ · 2026-09-28 Cached

LocUS is a novel method for targeted activation steering in large language models that restricts interventions to specific attention heads and a subspace of the unembedding matrix, improving performance while preserving general capabilities.

0 favorites 0 likes
← Back to home

Submit Feedback