© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 20623 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20623

INDEX

Explanations

unittest

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

kat

-0.08

Presence

-0.07

 cocktail

-0.07

 formats

-0.07

xdd

-0.06

okus

-0.06

 Hòa

-0.06

")]↵

-0.06

$sub

-0.06

jul

-0.06

POSITIVE LOGITS

 Finally

0.07

 Psych

0.07

 narrowly

0.06

 upward

0.06

��

0.06

uracion

0.06

orning

0.06

ЎыџN

0.06

 unittest

0.06

Finally

0.06

Activations Density 0.001%

No Known Activations