© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

LLAMA3.1-8B-IT · 3-RESID-POST-AA · 93612 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
3-RESID-POST-AA
93612

INDEX

Explanations

:

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_3/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.3.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

監

-0.07

 skyrocket

-0.07

き

-0.07

Speaking

-0.06

IG

-0.06

 iterators

-0.06

cz

-0.06

维

-0.06

 Removes

-0.06

满

-0.06

POSITIVE LOGITS

_renderer

0.07

callable

0.06

 pObj

0.06

 Burl

0.06

 самов

0.06

 Bacon

0.06

malı

0.06

 Saras

0.06

ximo

0.06

 Intl

0.06

Activations Density 0.073%

No Known Activations