© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B · 17-LLAMASCOPE-RES-131K · 15118 ｜ Neuronpedia

Home
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B (Base)
Residual Stream
17-LLAMASCOPE-RES-131K
15118

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

adge

-0.07

“

-0.07

:-

-0.06

 defer

-0.06

 Samuel

-0.06

 ÂŃ

-0.06

kte

-0.06

-0.06

-0.05

agination

-0.05

POSITIVE LOGITS

ovÃŃ

0.07

 ÑıÐ³Ð¾Ð´

0.07

izzo

0.07

iming

0.07

 dobrÃ©

0.07

 tarz

0.07

theless

0.07

çľ

0.07

Ì§

0.07

ãĤŃãĥ¼

0.07

Activations Density 0.000%

No Known Activations

This feature has no known activations.