Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders

Abstract

The mechanisms behind multilingual capabilities in Large Language Models (LLMs) have been examined using neuron-based or internal-activation-based methods. However, these methods often face challenges such as superposition and layer-wise activation variance, which limit their reliability. Sparse Autoencoders (SAEs) offer a more nuanced analysis by decomposing the activations of LLMs into a sparse linear combination of SAE features. We introduce a novel metric to assess the monolinguality of features obtained from SAEs, discovering that some features are strongly related to specific languages. Additionally, we show that ablating these SAE features only significantly reduces abilities in one language of LLMs, leaving others almost unaffected. Interestingly, we find some languages have multiple synergistic SAE features, and ablating them together yields greater improvement than ablating individually. Moreover, we leverage these SAE-derived language-specific features to enhance steering vectors, achieving control over the language generated by LLMs.

Publication
In ACL 2025

Citation:

@article{deng2025unveiling,
  title={Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders},
  author={Deng, Boyi and Wan, Yu and Zhang, Yidan and Yang, Baosong and Feng, Fuli},
  journal={arXiv preprint arXiv:2505.05111},
  year={2025}
}
Boyi Deng
Boyi Deng
邓博以
Fuli Feng
Fuli Feng
冯福利 教授