© 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

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 92890 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
92890

INDEX

Explanations

results

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 fluor

-0.07

 JPanel

-0.07

ा-

-0.06

 enzymes

-0.06

 misinformation

-0.06

 incentiv

-0.06

-0.06

Faculty

-0.06

opathy

-0.06

ì

-0.06

POSITIVE LOGITS

д

0.06

Term

0.06

个

0.06

шили

0.06

 breaches

0.06

 intimate

0.06

(Product

0.06

 boot

0.06

 burnt

0.06

 Compile

0.06

Activations Density 0.001%

No Known Activations