SEONGLAND

Welcome

Seonglae Cho

Research Scientist

Research scientist focused on LLM safety, interpretability, and steering. Building tools to understand and control language model behavior.

Scholar GitHub LinkedIn Twitter

News

2026.02 CRL paper published on arXiv
2026.02 Confidence Manifold paper published on arXiv
2025.08 CorrSteer paper published on arXiv
2025 FaithfulSAE accepted at ACL 2025 SRW
2025 LibVulnWatch accepted at ICML 2025 TAIG

Research Interests

LLM Safety Mechanistic Interpretability Sparse Autoencoders Steering Vectors Summarization

Mindset

Philosophy Optimistic Nihilism
Consciousness Bundle Theory
Prediction Statistical Thinking , Techno Optimism
Future Technological Singularity , Culture War
Planning GTD , RICE Framework
Creation First Principles Thinking
Attitude Critical Thinking
Computing Extended Church-Turing Thesis