© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

LLAMA3.1-8B · 17-LLAMASCOPE-RES-131K · 82967 ｜ Neuronpedia

Home
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B (Base)
Residual Stream
17-LLAMASCOPE-RES-131K
82967

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

USA

-0.06

egen

-0.05

 lifecycle

-0.05

 cannons

-0.05

-0.05

gens

-0.05

 behavior

-0.05

 motivated

-0.05

 dialog

-0.05

rack

-0.05

POSITIVE LOGITS

Ã¼z

0.07

æļ

0.07

ewis

0.07

kh

0.07

jian

0.07

fÃ¼g

0.07

ê·ł

0.07

 Ziel

0.07

llum

0.07

/Instruction

0.07

Activations Density 0.000%

No Known Activations

This feature has no known activations.