© 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 · 9615 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
9615

INDEX

Explanations

="

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

 Revised

-0.07

Neg

-0.07

 revised

-0.06

Radius

-0.06

 Davis

-0.06

_today

-0.06

Marvel

-0.06

REL

-0.06

-Length

-0.06

neg

-0.06

POSITIVE LOGITS

	Block

0.07

 grö

0.07

 اتفاق

0.06

칼

0.06

特色

0.06

kaz

0.06

kez

0.06

築

0.06

 stockings

0.06

 Εθν

0.06

Activations Density 0.003%

No Known Activations