© 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 · 57890 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
57890

INDEX

Explanations

are

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

ữ

-0.07

рег

-0.06

serializer

-0.06

Sh

-0.06

政府

-0.06

 yeter

-0.06

 Best

-0.06

-0.06

_zero

-0.06

 yaklaş

-0.06

POSITIVE LOGITS

\Auth

0.06

 certificate

0.06

certificate

0.06

_die

0.06

enable

0.06

 commun

0.06

 DataManager

0.06

 LinearLayout

0.06

xs

0.06

并

0.06

Activations Density 0.008%

No Known Activations