Paper recorded by Signals 4 on 2026-09-11 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-11 on arXiv · recorded by Signals 4 on 2026-09-14
Category: cs.AI · 人工智能 · first seen 2026-09-14
Fine-grained control of language model behaviors (e.g., steering) is among the more actionable outcomes of interpretability research. For binary concepts such as refusal, a single direction in activation space often suffices for steering. However, many concepts are not binary: Animals and Countries contain many subcategories, each with multiple instances. For these concepts, the search space over