© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 46098 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
46098

INDEX

Explanations

from

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

visions

-0.07

 retrieve

-0.07

estion

-0.07

ीक

-0.06

.mainloop

-0.06

.publish

-0.06

.twig

-0.06

 nemůže

-0.06

_IList

-0.06

 cantidad

-0.06

POSITIVE LOGITS

 standart

0.07

ιβ

0.07

Jur

0.06

 isot

0.06

vely

0.06

 Kimber

0.06

Hunter

0.06

 spolup

0.06

Vys

0.06

Ukr

0.06

Activations Density 0.014%

No Known Activations