© 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

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 553 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
553

INDEX

Explanations

ëĮĢ íĻĶ, å¤§ éĽª

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf

Configuration

Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑĩÐ°Ñģ

-0.10

íķĻ

-0.09

-0.09

Metrics

-0.09

/am

-0.08

Mou

-0.08

º¼

-0.08

ogg

-0.08

chart

-0.08

swift

-0.08

POSITIVE LOGITS

 diá»ĩn

0.11

-scale

0.11

oud

0.10

éĥ½ä¼ļ

0.10

fully

0.10

-grand

0.09

 scale

0.09

à¤¾à¤¯à¤ķ

0.09

å¤§çļĦ

0.09

wner

0.09

Activations Density 0.017%

No Known Activations