© 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 · 130043 ｜ Neuronpedia

Home
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B (Base)
Residual Stream
17-LLAMASCOPE-RES-131K
130043

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

allo

-0.07

-0.07

 VÃ¡c

-0.07

-------------</

-0.07

ationship

-0.07

inesis

-0.07

ediator

-0.07

DataExchange

-0.07

bjerg

-0.07

ollo

-0.07

POSITIVE LOGITS

 itself

0.06

-c

0.06

ale

0.06

ange

0.06

arest

0.06

 precinct

0.05

SPATH

0.05

 Patrol

0.05

0.05

der

0.05

Activations Density 0.000%

No Known Activations

This feature has no known activations.