Activation probes
Named by 2 kept items in this workspace.
Search every workspace for Activation probes. It matches the name as written, so it can find other things that share it.
The items that name it 2
Lightweight classifiers on a model's internal activations, used as the first monitoring layer (L0) and tuned for high recall; a random 5 percent of unflagged traffic is also passed on.
All techniques in this workspace.