All people

Researcher

Adly Templeton

AT

Member of Technical Staff at Anthropic

Templeton leads work that makes the internal concepts of large models more legible. She co-led Scaling Monosemanticity, which extracted millions of interpretable features from Claude 3 Sonnet and showed that features linked to deception, bias or power-seeking can causally affect its behavior.

See something inaccurate or outdated?

Background

Current role
Member of Technical Staff Mar 2023-present
Previously
2022-2023ML Engineer,
2020-2022Software Engineer,
About this data

Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.

Last editorial review: August 9, 2026

Citation Trend

2 snapshots
Citation history from Aug 25, '25 to Jun 15, '26999Aug 25, '25Jun 15, '26
9citations as of Jun 15, '260 since Aug 25, '25
For today’s citation count and citations per paper, visit Google Scholar.