© 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 · 35905 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
35905

INDEX

Explanations

years following 191

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

tem

-0.12

ummer

-0.11

um

-0.11

ov

-0.10

-0.10

umm

-0.10

''"

-0.10

craft

-0.09

etti

-0.09

::::::::::::::::

-0.09

POSITIVE LOGITS

st

0.16

ration

0.12

allas

0.11

stal

0.11

stk

0.11

inals

0.10

STALL

0.10

rapper

0.09

apolis

0.09

uring

0.09

Activations Density 0.017%

No Known Activations