© 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 · 27-RESID-POST-AA · 33808 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
33808

INDEX

Explanations

the

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

marine

-0.07

CMS

-0.07

.href

-0.06

 destiny

-0.06

.double

-0.06

►

-0.06

 sufferers

-0.06

-0.06

 κυ

-0.06

DESCRIPTION

-0.06

POSITIVE LOGITS

Seleccion

0.06

 familial

0.06

Bil

0.06

��

0.06

 gần

0.06

celed

0.06

orough

0.06

 Hava

0.06

ř

0.06

 simulate

0.06

Activations Density 0.029%

No Known Activations