© 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 · 15-RESID-POST-AA · 61607 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
61607

INDEX

Explanations

false/null/zero

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

 glGet

-0.06

 thoải

-0.06

DV

-0.06

 amplifier

-0.06

swagger

-0.06

na

-0.05

iT

-0.05

 rustic

-0.05

.Arrays

-0.05

TextArea

-0.05

POSITIVE LOGITS

бе

0.08

Refer

0.07

 فت

0.07

数学

0.07

])
↵
↵

0.07

|()↵

0.07

 ＼↵

0.07

ครอบ

0.07

achte

0.06

 DISTRIBUT

0.06

Activations Density 0.019%

No Known Activations