© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 27-RESID-POST-AA · 17381 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
17381

INDEX

Explanations

scientific articles

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

loi

-0.07

 себе

-0.07

/B

-0.06

 stepping

-0.06

 Columns

-0.06

 refreshToken

-0.06

طر

-0.06

.logging

-0.06

-0.06

当前

-0.06

POSITIVE LOGITS

땅

0.06

벌

0.06

 mbox

0.06

_totals

0.06

.Framework

0.06

ッグ

0.06

 FileWriter

0.06

isse

0.06

(boost

0.06

@dynamic

0.06

Activations Density 0.299%

No Known Activations