© 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 · 58957 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
58957

INDEX

Explanations

Arginine and enzymes

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

-0.07

еров

-0.07

 sucking

-0.06

 loud

-0.06

 expresses

-0.06

وص

-0.06

los

-0.06

ój

-0.06

 Dealers

-0.06

...,

-0.06

POSITIVE LOGITS

.***.***

0.06

_TRANSL

0.06

เก

0.06

":[-

0.06

<vector

0.06

 Attach

0.06

 marin

0.06

사랑

0.06

 ************************

0.06

dığ

0.06

Activations Density 0.005%

No Known Activations