5x Model Organisms of Misalignment
Collection
Five Qwen3-8B LoRAs exhibiting distinct oversight-gated misalignments, each paired with a matched control. • 11 items • Updated
Boyd Kane
beyarkay
AI & ML interests
None yet
Recent Activity
updated a collection 19 days ago
5x Model Organisms of Misalignment updated a dataset 19 days ago
beyarkay/5x-limited-parameter-finetuning published a dataset 19 days ago
beyarkay/5x-limited-parameter-finetuningOrganizations
None yet
updated a
collection 19 days ago
updated a
dataset 19 days ago
published a
dataset 19 days ago
updated a
collection 19 days ago
updated a
model 19 days ago
published a
model 19 days ago
updated a
model 19 days ago
published a
model 19 days ago
updated a
model 19 days ago
published a
model 19 days ago
updated a
model 19 days ago