On the Biology of a Large Language Model
Lindsey et al., 2025, On the Biology of a Large Language Model (Transformer Circuits Thread)
Subscriber deck — free during early access
1 cards in “Life of a Jailbreak” · whole deck
Life of a Jailbreak
- Why did Claude 3.5 Haiku start answering a jailbreak that spelled “BOMB” from the first letters of words, and when did it refuse?It assembled the letters one by one without internally recognizing the word, so harmful-request features did not fire. Once it wrote “To make a bomb”, grammar and self-consistency kept it going, and it refused only at a new sentence (“However, I cannot…”), where new-sentence features helped refusal win out.
- Lindsey et al., 2025, On the Biology of a Large Language Model (Transformer Circuits Thread), Life of a Jailbreak
Source
- Jack Lindsey, Wes Gurnee, Emmanuel Ameisen, Brian Chen, Adam Pearce, Nicholas L. Turner, Craig Citro, David Abrahams, Shan Carter, Basil Hosmer, Jonathan Marcus, Michael Sklar, Adly Templeton, Trenton Bricken, Callum McDougall, Hoagy Cunningham, Thomas Henighan, Adam Jermyn, Andy Jones, Andrew Persic, Zhenyi Qi, T. Ben Thompson, Sam Zimmerman, Kelley Rivoire, Thomas Conerly, Chris Olah and Joshua Batson. 2025. On the Biology of a Large Language Model. In Transformer Circuits Thread. https://transformer-circuits.pub/2025/attribution-graphs/biology.html