Steering Large Language Models with Feature Guided Activation Additions
Effective and reliable control over large language model (LLM) behavior is a significant challenge. While activation steering methods, which add steering vectors to a model's hidden states, are a promising approach, existing techniques often lack precision and interpretability in how they influence model outputs. We introduce Feature Guided Activation Additions (FGAA), a novel activation steering method that leverages insights from Contrastive Activation Addition (CAA) and Sparse Autoencoder-Targeted Steering (SAE-TS). By operating in the latent space of a Sparse Autoencoder (SAE) and employing optimization techniques to select desired SAE features, FGAA constructs precise steering vectors that provide better steering effects while maintaining coherence of steered model outputs. In this regard, evaluations on Gemma-2-2B and Gemma-2-9B models across various steering tasks demonstrate that FGAA outperforms existing steering methods of CAA, SAE decoder steering, and SAE-TS. Our results also highlight important trade-offs between steering scale and general model capabilities that are consistent across all tested steering methods.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderLanguage ModelingLanguage ModellingLarge Language ModelMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Efficient and accurate steering of Large Language Models through attention-guided feature learning
Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and…
Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potent…
Instruction FollowingUniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering
Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style…
Instruction FollowingManifold-Guided Attention Steering
Large language models frequently produce errors in reasoning tasks despite possessing the underlying knowledge required for correct reasoning. One possible approach to improve reasoning consistency is through activation …
Mathematical ReasoningCode GenerationODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
Activation steering, or representation engineering, offers a lightweight approach to align large language models (LLMs) by manipulating their internal activations at inference time. However, current methods suffer from t…