© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B · 17-LLAMASCOPE-RES-131K · 70603 ｜ Neuronpedia

Home
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B (Base)
Residual Stream
17-LLAMASCOPE-RES-131K
70603

INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĳ¢

-0.07

was

-0.06

adies

-0.06

 Normally

-0.06

-0.06

forgot

-0.06

Ced

-0.06

selected

-0.05

-0.05

astes

-0.05

POSITIVE LOGITS

sdale

0.07

0.07

umptech

0.07

 ,č↵

0.07

 compound

0.06

loven

0.06

uptime

0.06

ximity

0.06

.ISupportInitialize

0.06

AJOR

0.06

Activations Density 0.000%

No Known Activations

This feature has no known activations.