Cite
Notes
Only stored in your browser.
Attribution
Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
arXiv 2025
Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
arXiv 2024
Distilling Script Knowledge from Large Language Models for Constrained Language Planning
arXiv 2023
from 3 papers
Junxuan Wang
Wentao Shu
Xipeng Qiu
Zhengfu He
Charles Robert Jankowski
Deqing Yang
Frances Liu
Jiangjie Chen
Junping Zhang
Lingjie Chen