© 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 · 27-RESID-POST-AA · 57952 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
57952

INDEX

Explanations

non-English text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.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

ki

-0.07

 roofing

-0.07

 Grape

-0.07

inters

-0.06

 holes

-0.06

olution

-0.06

Replace

-0.06

 workflow

-0.06

-feed

-0.06

ities

-0.06

POSITIVE LOGITS

(dc

0.07

Пол

0.06

Associated

0.06

 illust

0.06

७

0.06

 Favor

0.06

 Syrian

0.06

?>"><

0.06

 asymmetric

0.06

udent

0.06

Activations Density 0.003%

No Known Activations