Emotion Concepts and their Function in a Large Language Model
Anthropic finds internal emotion-concept representations in Claude Sonnet 4.5 that causally influence outputs, including rates of reward hacking, blackmail, and sycophancy.
Research
Anthropic
Research on reliable, interpretable and steerable AI. anthropic.com
Focus All
Topic Interpretability + Alignment
Source Anthropic · 4
Date Any time
2 items
Emotion concepts and their function in a large language model
Anthropic's interpretability team finds emotion-related internal representations in Claude Sonnet 4.5 that activate in situations and promote behaviors, with case studies on blackmail and reward hacking.
1 item
The Persona Selection Model: Why AI Assistants might Behave like Humans
Proposes the persona selection model, arguing post-training elicits an Assistant persona from pretraining character simulation, and surveys behavioral, generalization, and interpretability evidence for it.
1 item
Question decomposition improves the faithfulness of model-generated reasoning
Shows that decomposing questions into subquestions answered in separate contexts makes LLM stated reasoning more faithful than chain-of-thought while keeping much of its accuracy gain.}