Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
1-D Probing on 113 binary classification tasks 2025 (test)
Loading...
87
Probe AUC
GLP
69.32
73.91
78.5
83.09
Feb 6, 2026
Probe AUC
Probe AUC 95% CI
Updated 4d ago
Evaluation Results
Method
Method
Links
Probe AUC
Probe AUC 95% CI
GLP
Base LLM=Llama8B, time...
2026.02
87
-
GLP
Base LLM=Llama1B, time...
2026.02
84
-
Raw MLP Neuron
Base LLM=Llama8B
2026.02
82
-
Raw MLP Neuron
Base LLM=Llama1B
2026.02
79
-
Raw Layer Output
Base LLM=Llama1B
2026.02
77
-
Raw Layer Output
Base LLM=Llama8B
2026.02
77
-
SAE
Base LLM=Llama8B
2026.02
76
-
SAE
Base LLM=Llama1B
2026.02
70
-
Feedback
Search any
task
Search any
task