7 papers
NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models
Weiqi Liu, Yongliang Miao, Haiyan Zhao +2
Neuron-level interpretation in large language models (LLMs) is fundamentally challenged by widespread polysemanticity, where individual neurons respond to multiple distinct semanti…
ContractEval: Benchmarking LLMs for Clause-Level Legal Risk Identification in Commercial Contracts
Shuang Liu, Zelong Li, Ruoyun Ma +2
The potential of large language models (LLMs) in specialized domains such as legal risk analysis remains underexplored. In response to growing interest in locally deploying open-so…
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
Haiyan Zhao, Xuansheng Wu, Fan Yang +3
Linear concept vectors effectively steer LLMs, but existing methods suffer from noisy features in diverse datasets that undermine steering robustness. We propose Sparse Autoencoder…
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
Dong Shu, Xuansheng Wu, Haiyan Zhao +2
Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional…
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
Dong Shu, Xuansheng Wu, Haiyan Zhao +4
Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted…
SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
Zirui He, Haiyan Zhao, Yiran Qiao +4
The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper p…