Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Q-learning
Findings
IC-062
Llama 3 70B implements temporal difference learning in-context for reward-based RL, with causally relevant SAE features in its residual stream, while Llama 3 8B performs at chance
[compared-to]
IC-064
The TD learning mechanism identified in Llama 3 70B generalizes to Gemma-2-27B and Qwen-2.5-72B across all three tasks
[compared-to]