© 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 · 15-RESID-POST-AA · 27896 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
27896

INDEX

Explanations

BERT/Net

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

.Transform

-0.07

#,

-0.07

.hibernate

-0.06

autorelease

-0.06

mys

-0.06

LoadIdentity

-0.06

 문화

-0.06

_mov

-0.06

яз

-0.06

-_

-0.06

POSITIVE LOGITS

0.07

EEDED

0.07

ОН

0.07

ORK

0.07

sections

0.07

oding

0.06

0.06

oded

0.06

orbit

0.06

odem

0.06

Activations Density 0.002%

No Known Activations