© 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

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 12832 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
12832

INDEX

Explanations

I suggest

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

als

-0.09

esta

-0.09

ID

-0.09

Vic

-0.09

 parity

-0.09

ats

-0.08

ak

-0.08

 Dirk

-0.08

ami

-0.08

EIF

-0.08

POSITIVE LOGITS

 suggest

0.16

 suggestion

0.14

 could

0.13

 offer

0.13

 suggests

0.12

can

0.11

uggest

0.11

 would

0.10

å»ºè®®

0.10

 Could

0.10

Activations Density 0.041%

No Known Activations