© 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 · 19-RESID-POST-AA · 84328 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
84328

INDEX

Explanations

lead

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

ann

-0.07

_UPDATED

-0.07

 kitten

-0.06

ogue

-0.06

-var

-0.06

 gadget

-0.06

никами

-0.06

 filthy

-0.06

 parody

-0.06

山市

-0.06

POSITIVE LOGITS

 Lead

0.09

Lead

0.09

 lead

0.08

lead

0.07

età

0.07

益

0.07

.summary

0.07

 Percent

0.07

#/

0.06

maktadır

0.06

Activations Density 0.008%

No Known Activations