
Christopher OlahResearcher
Anthropic
Co-founder
via Anthropic
Researcher
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See something inaccurate or outdated?
AnthropicWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Last editorial review: August 9, 2026