Prior work argues that refusal in large language models is mediated by a single activation-space direction, enabling effective steering and ablation. We show that this account is incomplete. Across eleven categories of refusal and non-compliance, including safety, incomplete or unsupported requests, anthropomorphization, and over-refusal, we find that these refusal behaviors correspond to geometrically distinct directions in activation space. Yet despite this diversity, linear steering along any refusal-related direction produces nearly identical refusal to over-refusal trade-offs, acting as a shared one-dimensional control knob. The primary effect of different directions is not whether the model refuses, but how it refuses.
Cite
@article{arxiv.2602.02132,
title = {There Is More to Refusal in Large Language Models than a Single Direction},
author = {Faaiz Joad and Majd Hawasly and Sabri Boughorbel and Nadir Durrani and Husrev Taha Sencar},
journal= {arXiv preprint arXiv:2602.02132},
year = {2026}
}