Scholar
Lihao Sun
Google Scholar ID: 7YG8vXEAAAAJ
University of Chicago
AI
Mechanistic Interpretability
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2
H-index
1
i10-index
0
Publications
2
Co-authors
6
list available
Contact
Email
slhleosun@uchicago.edu
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
Publications
4 items
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
2026
Cited
0
Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control
2026
Cited
0
Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
2025
Cited
0
The Geometry of Self-Verification in a Task-Specific Reasoning Model
2025
Cited
0
Resume (English only)
Co-authors
6 total
Xuechunzi Bai
Assistant Professor of Psychology, University of Chicago
Andrew Lee
Harvard University
Martin Wattenberg
Harvard University / Google Research
Valentin Hofmann
Allen Institute for AI & University of Washington
Fernanda Viégas
Google, Harvard
Chengzhi Mao
Assistant Professor, Rutgers University
