Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,5 @@
|
|
|
|
|
|
|
|
| 1 |
Refer to our [code repo](https://github.com/Hanpx20/SafeSwitch) for usage.
|
| 2 |
|
| 3 |
`refusal_head.pth`: the refusal head.
|
|
|
|
| 1 |
+
Model for paper [SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals](arxiv.org/abs/2502.01042).
|
| 2 |
+
|
| 3 |
Refer to our [code repo](https://github.com/Hanpx20/SafeSwitch) for usage.
|
| 4 |
|
| 5 |
`refusal_head.pth`: the refusal head.
|