© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 93696 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
93696

INDEX

Explanations

worked

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

 ساز

-0.07

-May

-0.07

┴

-0.06

 Github

-0.06

,msg

-0.06

 آیا

-0.06

 詳細

-0.06

 roadmap

-0.06

 риз

-0.06

ений

-0.06

POSITIVE LOGITS

0.07

kerja

0.07

 worked

0.07

 обязан

0.07

 working

0.07

 Working

0.07

 Seal

0.06

 cria

0.06

 executives

0.06

cor

0.06

Activations Density 0.024%

No Known Activations