© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 27-RESID-POST-AA · 45228 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
45228

INDEX

Explanations

political activism

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

và

-0.07

 exits

-0.06

ของค

-0.06

③

-0.06

 grinned

-0.06

 directions

-0.06

 calendars

-0.06

 taxes

-0.06

losti

-0.06

utan

-0.06

POSITIVE LOGITS

 crossed

0.07

 yapacak

0.07

іїв

0.07

 Legal

0.06

 HARD

0.06

 Constants

0.06

Hur

0.06

OCR

0.06

 Pendant

0.06

 مشاهده

0.06

Activations Density 0.038%

No Known Activations