© 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 · 128206 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
128206

INDEX

Explanations

Quotations

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

cripcion

-0.07

TSA

-0.06

&utm

-0.06

нах

-0.06

iri

-0.06

asu

-0.06

 lợi

-0.06

credits

-0.06

_SCALE

-0.06

Mbps

-0.06

POSITIVE LOGITS

je

0.07

структор

0.07

 Gerald

0.07

izophren

0.07

_prog

0.06

 Joker

0.06

 Yellow

0.06

.x

0.06

(image

0.06

youtube

0.06

Activations Density 0.001%

No Known Activations