© 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 · 77599 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
77599

INDEX

Explanations

Text

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

lags

-0.07

elm

-0.07

Armor

-0.07

 poder

-0.06

rawn

-0.06

LIBINT

-0.06

よう

-0.06

Leon

-0.06

団

-0.06

出す

-0.06

POSITIVE LOGITS

[data

0.07

 Text

0.07

 Compact

0.07

tax

0.07

 selecting

0.07

TEXT

0.07

.cd

0.07

Articles

0.07

 simplex

0.06

 prospective

0.06

Activations Density 0.001%

No Known Activations