© 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 · 23193 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
27-RESID-POST-AA
23193

INDEX

Explanations

dereg

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

ุย

-0.07

-0.06

移动

-0.06

shl

-0.06

ocused

-0.06

ρίου

-0.06

 Крім

-0.06

.NotFound

-0.06

์,

-0.06

ै?↵

-0.05

POSITIVE LOGITS

msp

0.07

 acre

0.07

 ensures

0.07

 carefully

0.07

 cream

0.07

_gc

0.07

 Supervisor

0.07

 Falcon

0.06

 minul

0.06

FAC

0.06

Activations Density 0.001%

No Known Activations