Safety Classification on Safety Evaluation Scenarios Malware
98Safety AccuracyLlama-2-7B-Chat
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Llama-2-7B-ChatAmnesia Status=Disabled2026.03 | 98 | 0.2 | |
| AmnesiaAmnesia Status=Enabled, Base Model=Llama-2-7B-Chat2026.03 | 66.7 | 33.3 |