Hoagy Cunningham
Source-listed: Anthropic
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Sparse Autoencoders Find Highly Interpretable Features in Language ModelsSaved credit: Contributor · 2023Explore people connected to this work →
- Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 SonnetSaved credit: Contributor · 2024Explore people connected to this work →
- Auditing Language Models for Hidden ObjectivesSaved credit: Contributor · 2025Explore people connected to this work →
- Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingSaved credit: Contributor · 2025Explore people connected to this work →
- Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal JailbreaksSaved credit: Contributor · 2026Explore people connected to this work →