© 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 · 46288 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
46288

INDEX

Explanations

.jupiter

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

 frontend

-0.06

.standard

-0.06

 Recogn

-0.06

 Derby

-0.06

-0.06

refresh

-0.06

StringEncoding

-0.06

 Move

-0.06

<strong

-0.06

록

-0.06

POSITIVE LOGITS

 války

0.07

iş

0.07

.sm

0.07

(IL

0.07

 сказать

0.07

 dagger

0.07

ый

0.06

ấp

0.06

ík

0.06

lover

0.06

Activations Density 0.002%

No Known Activations