© 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 · 7-RESID-POST-AA · 22489 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
22489

INDEX

Explanations

.state

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

ardware

-0.08

φή

-0.07

 lore

-0.07

],

-0.07

 receptors

-0.06

OPER

-0.06

헤

-0.06

 anak

-0.06

 Rencontres

-0.06

Venue

-0.06

POSITIVE LOGITS

.state

0.07

 savvy

0.07

"""
↵
↵

0.06

 %%↵

0.06

ğin

0.06

って

0.06

 Počet

0.06

 PartialView

0.06

 frac

0.06

 diğer

0.06

Activations Density 0.001%

No Known Activations