© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.3-70B-IT · 50-RESID-POST-GF · 42140 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
42140

INDEX

Explanations

instructions to read

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

Negative Logits

acco

-0.10

ording

-0.09

uthor

-0.09

Sag

-0.09

upa

-0.09

RequestId

-0.09

 sage

-0.09

å°¾

-0.08

WithString

-0.08

ILT

-0.08

POSITIVE LOGITS

ied

0.20

just

0.20

æĩĤ

0.17

iness

0.15

 carefully

0.15

ym

0.14

ies

0.14

 closely

0.14

ystate

0.14

ily

0.14

Activations Density 0.033%

No Known Activations