© 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 · 15-RESID-POST-AA · 83176 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
83176

INDEX

Explanations

concepts

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

恶

-0.07

jez

-0.07

anon

-0.07

orz

-0.06

discord

-0.06

 their

-0.06

CLA

-0.06

Steel

-0.06

ale

-0.06

-0.06

POSITIVE LOGITS

HomePage

0.07

 المنطقة

0.06

 العالمية

0.06

0.06

chat

0.06

.Entry

0.06

 côt

0.06

 weekday

0.06

imleri

0.06

ินการ

0.06

Activations Density 0.674%

No Known Activations