Tracing the thoughts of a large language model \ Anthropic
anthropic.com · 3,175 words · saved by 18 readers
Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms
Interpretability Tracing the thoughts of a large language model Mar 27, 2025 Read the paper Language models like Claude aren't programmed directly by humans—instead, they‘re trained on large amounts of data. During that training process, they learn their own strategies to solve problems. These strategies are encoded in the billions of computations a model performs for every word it writes. They arrive inscrutable to us, the model’s developers. This means that we don’t understand how models do most of the things they do. Knowing how models like Claude think would allow us to have a better under
saved by
- Winnie Xu
- Elizabeth Qiu
- Ruozhen Gong
- Freeman Jiang
- Shivam Siddaiya
- Samuel Lo
- Jennifer Zhao
- Saloni Shenoy
- Lâm Vũ
- Lydia Nottingham
- Sarah
- Yingfan
related reading
- On the Biology of a Large Language Modeltransformer-circuits.pub
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- Natural Language Autoencoders \ Anthropicanthropic.com
- Mapping the Mind of a Large Language Model \ Anthropicanthropic.com
- A global workspace in language models \ Anthropicanthropic.com
- Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
- Emergent introspective awareness in large language models \ Anthropicanthropic.com
- Tracing the Thoughts of a Large Language Model — LessWronglesswrong.com
- Emotion concepts and their function in a large language model \ Anthropicanthropic.com
- Transformer Circuits Threadtransformer-circuits.pub
- How AI Is Learning to Think in Secretnickandresen.substack.com
- Mapping the mind of a large language model \ Anthropicanthropic.com