© 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 · 36657 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
36657

INDEX

Explanations

ham

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

 crane

-0.08

`,

-0.07

 diagnoses

-0.07

 کیف

-0.06

 CROSS

-0.06

ADIUS

-0.06

 Rental

-0.06

 guide

-0.06

 Label

-0.06

 dissemination

-0.06

POSITIVE LOGITS

τύ

0.08

ognitive

0.07

 GLfloat

0.07

닥

0.06

dll

0.06

 дра

0.06

 Çağ

0.06

 culprit

0.06

.innerHeight

0.06

ุ่

0.06

Activations Density 0.001%

No Known Activations