© 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 · 11-RESID-POST-AA · 46572 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
46572

INDEX

Explanations

for

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

 Mathematics

-0.07

 linewidth

-0.07

_variant

-0.07

_SEG

-0.06

HORT

-0.06

_STENCIL

-0.06

花

-0.06

 }
↵
↵

-0.06

PAGE

-0.06

atisfaction

-0.06

POSITIVE LOGITS

 brilliantly

0.07

fred

0.06

 Rafael

0.06

,@

0.06

EZ

0.06

 voor

0.06

STOP

0.06

 grows

0.06

CESS

0.06

for

0.06

Activations Density 0.059%

No Known Activations