Saved in:
Bibliographic Details
Main Authors: He, Zhengfu, Shu, Wentao, Ge, Xuyang, Chen, Lingjie, Wang, Junxuan, Zhou, Yunhua, Liu, Frances, Guo, Qipeng, Huang, Xuanjing, Wu, Zuxuan, Jiang, Yu-Gang, Qiu, Xipeng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.20526
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910672494788608
author He, Zhengfu
Shu, Wentao
Ge, Xuyang
Chen, Lingjie
Wang, Junxuan
Zhou, Yunhua
Liu, Frances
Guo, Qipeng
Huang, Xuanjing
Wu, Zuxuan
Jiang, Yu-Gang
Qiu, Xipeng
author_facet He, Zhengfu
Shu, Wentao
Ge, Xuyang
Chen, Lingjie
Wang, Junxuan
Zhou, Yunhua
Liu, Frances
Guo, Qipeng
Huang, Xuanjing
Wu, Zuxuan
Jiang, Yu-Gang
Qiu, Xipeng
contents Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant challenge. We introduce a suite of 256 SAEs, trained on each layer and sublayer of the Llama-3.1-8B-Base model, with 32K and 128K features. Modifications to a state-of-the-art SAE variant, Top-K SAEs, are evaluated across multiple dimensions. In particular, we assess the generalizability of SAEs trained on base models to longer contexts and fine-tuned models. Additionally, we analyze the geometry of learned SAE latents, confirming that \emph{feature splitting} enables the discovery of new features. The Llama Scope SAE checkpoints are publicly available at~\url{https://huggingface.co/fnlp/Llama-Scope}, alongside our scalable training, interpretation, and visualization tools at \url{https://github.com/OpenMOSS/Language-Model-SAEs}. These contributions aim to advance the open-source Sparse Autoencoder ecosystem and support mechanistic interpretability research by reducing the need for redundant SAE training.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20526
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
He, Zhengfu
Shu, Wentao
Ge, Xuyang
Chen, Lingjie
Wang, Junxuan
Zhou, Yunhua
Liu, Frances
Guo, Qipeng
Huang, Xuanjing
Wu, Zuxuan
Jiang, Yu-Gang
Qiu, Xipeng
Machine Learning
Computation and Language
Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant challenge. We introduce a suite of 256 SAEs, trained on each layer and sublayer of the Llama-3.1-8B-Base model, with 32K and 128K features. Modifications to a state-of-the-art SAE variant, Top-K SAEs, are evaluated across multiple dimensions. In particular, we assess the generalizability of SAEs trained on base models to longer contexts and fine-tuned models. Additionally, we analyze the geometry of learned SAE latents, confirming that \emph{feature splitting} enables the discovery of new features. The Llama Scope SAE checkpoints are publicly available at~\url{https://huggingface.co/fnlp/Llama-Scope}, alongside our scalable training, interpretation, and visualization tools at \url{https://github.com/OpenMOSS/Language-Model-SAEs}. These contributions aim to advance the open-source Sparse Autoencoder ecosystem and support mechanistic interpretability research by reducing the need for redundant SAE training.
title Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2410.20526