Disentangling Steering Vectors

2026-09-07

AI Summary

本文提出一种方法解决大型语言模型中激活向量包含多重概念导致的不可预测控制效果问题，通过构建稀疏自编码器分解这些向量，实现对模型行为的精确控制。

Abstract

Activation steering has emerged as a lightweight, inference-time approach to control the behavior of Large Language Models (LLMs). However, traditional steering vectors used to intervene in LLMs'activations, such as those derived from the difference-in-means method, tend to entangle multiple semantic and stylistic concepts into a single composite direction, leading to unpredictable steering effects. Our core objective is to disentangle this composite direction into its constituent concepts. To this end, we propose Steering Vector Dissection, a framework to explicitly isolate individual and semantically consistent features from these composite directions. Specifically, we pair positive and negative activations and take their differences to generate a set of instance-level steering vectors, and train a dedicated Sparse Autoencoder (SAE) directly on them. Quantitative evaluations across two datasets, two models, and two intervention depths show that our method yields a set of semantically consistent basis vectors whose steering effects are mutually distinguishable. Furthermore, we show that this disentanglement enables precise control over model behaviors.

Problem

• activation steering
• large language models
• steering vectors
• disentangling

Innovation

• Steering Vector Dissection
• Sparse Autoencoder
• disentanglement
• semantically consistent basis vectors