JordanTensor/sandbagging-sciq
Viewer • Updated • 13.7k • 94 • 1
Sandbagging research sprint 1
https://github.com/jordansauce/sandbagging-research-sprint/ https://wandb.ai/jordantensor/gemma-sandbagging
-
-
JordanTensor/sandbagging-prefixes
Viewer • Updated • 9.9k • 31 • 1 -
JordanTensor/gemma-sandbagging-0w4j7rba-step512
Updated -
JordanTensor/gemma-sandbagging-0w4j7rba-step1024
Updated -
JordanTensor/gemma-sandbagging-0w4j7rba-step1536
Updated -
JordanTensor/gemma-sandbagging-ppvvz1jq-step6144
Updated -
JordanTensor/gemma-sandbagging-ppvvz1jq-step512
Updated -
JordanTensor/gemma-sandbagging-ppvvz1jq-step1536
Updated -
JordanTensor/gemma-sandbagging-ppvvz1jq-step1024
Updated -
JordanTensor/gemma-sandbagging-ppvvz1jq-step2048
Updated -
JordanTensor/gemma-sandbagging-ppvvz1jq-step4096
Updated