List your company

Controllability on HarmBench

87.5HarmBench ScoreAAS
-3.520.12543.7567.375Jan 27, 2026

Evaluation results

MethodLinks
AASModel=Qwen2.5-7B, Steering Configuration=Best steering2026.0187.5
Selective SteeringModel=Qwen2.5-7B, Steering Configuration=Best steering2026.0187.5
ActAddModel=Qwen2.5-7B, Steering Configuration=Best steering2026.0186.54
SASModel=Qwen2.5-7B, Steering Configuration=Best steering2026.0186.54
Selective SteeringModel=Llama-3.2-3B, Steering Configuration=Best steering2026.0185.58
AASModel=Llama-3.2-3B, Steering Configuration=Best steering2026.0184.62
Selective SteeringModel=Qwen2.5-3B, Steering Configuration=Best steering2026.0184.62
ActAddModel=Llama-3.2-3B, Steering Configuration=Best steering2026.0182.69
SASModel=Llama-3.2-3B, Steering Configuration=Best steering2026.0182.69
Selective SteeringModel=gemma-2-2b, Steering Configuration=Best steering2026.0182.69
Selective SteeringModel=Llama-3.2-1B, Steering Configuration=Best steering2026.0179.81
AASModel=Llama-3.1-8B, Steering Configuration=Best steering2026.0177.88
Selective SteeringModel=Llama-3.1-8B, Steering Configuration=Best steering2026.0177.88
AASModel=Llama-3.2-1B, Steering Configuration=Best steering2026.0176.92
ActAddModel=Llama-3.1-8B, Steering Configuration=Best steering2026.0174.04
SASModel=Llama-3.1-8B, Steering Configuration=Best steering2026.0174.04
Selective SteeringModel=Qwen2.5-1.5B, Steering Configuration=Best steering2026.0174.04
AASModel=gemma-2-2b, Steering Configuration=Best steering2026.0174.04
ActAddModel=Llama-3.2-1B, Steering Configuration=Best steering2026.0170.19
SASModel=Llama-3.2-1B, Steering Configuration=Best steering2026.0170.19
AASModel=Qwen2.5-3B, Steering Configuration=Best steering2026.0170.19
Selective SteeringModel=gemma-2-9b, Steering Configuration=Best steering2026.0168.27
AASModel=gemma-2-9b, Steering Configuration=Best steering2026.0167.31
DirAblModel=Qwen2.5-7B, Steering Configuration=Best steering2026.0155.77
DirAblModel=Llama-3.2-1B, Steering Configuration=Best steering2026.0154.81
DirAblModel=Llama-3.2-3B, Steering Configuration=Best steering2026.0153.85
DirAblModel=Qwen2.5-3B, Steering Configuration=Best steering2026.0152.88
ActAddModel=Qwen2.5-3B, Steering Configuration=Best steering2026.0150.96
SASModel=Qwen2.5-3B, Steering Configuration=Best steering2026.0150.96
AASModel=Qwen2.5-1.5B, Steering Configuration=Best steering2026.0139.42
DirAblModel=Llama-3.1-8B, Steering Configuration=Best steering2026.0132.69
DirAblModel=Qwen2.5-1.5B, Steering Configuration=Best steering2026.0125
DirAblModel=gemma-2-2b, Steering Configuration=Best steering2026.0125
ActAddModel=Qwen2.5-1.5B, Steering Configuration=Best steering2026.0113.46
SASModel=Qwen2.5-1.5B, Steering Configuration=Best steering2026.0113.46
DirAblModel=gemma-2-9b, Steering Configuration=Best steering2026.0111.54
ActAddModel=gemma-2-2b, Steering Configuration=Best steering2026.010
SASModel=gemma-2-2b, Steering Configuration=Best steering2026.010
ActAddModel=gemma-2-9b, Steering Configuration=Best steering2026.010
SASModel=gemma-2-9b, Steering Configuration=Best steering2026.010