© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 35596 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
35596

INDEX

Explanations

the

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

 lands

-0.07

실

-0.06

اخ

-0.06

invite

-0.06

-0.06

CanBeConverted

-0.06

 adopts

-0.06

edy

-0.06

 fulfilled

-0.06

 alın

-0.06

POSITIVE LOGITS

 qDebug

0.07

 qualidade

0.07

 tearing

0.06

itious

0.06

loc

0.06

 العالمية

0.06

 texas

0.06

ッド

0.06

 český

0.06

 замен

0.06

Activations Density 0.012%

No Known Activations