© 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 · 21875 ｜ Neuronpedia

Home
Llama3.3-70B-IT
50-RESID-POST-GF
21875

INDEX

Explanations

om/omn prefix words

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

Ngh

-0.10

erg

-0.10

etr

-0.09

Mir

-0.09

duto

-0.08

 motor

-0.08

olls

-0.08

cot

-0.08

ingham

-0.08

 IDEA

-0.08

POSITIVE LOGITS

lette

0.16

Omn

0.14

omn

0.13

aggio

0.13

Om

0.13

LETTE

0.12

kara

0.12

om

0.12

Om

0.12

egas

0.11

Activations Density 0.025%

No Known Activations