© 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 · 20930 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20930

INDEX

Explanations

names

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

girls

-0.07

gow

-0.07

going

-0.07

円

-0.06

под

-0.06

go

-0.06

ीकरण

-0.06

ับผ

-0.06

 highway

-0.06

 computations

-0.06

POSITIVE LOGITS

Л

0.08

FileSize

0.07

ulması

0.07

 requis

0.06

 SAVE

0.06

ตน

0.06

Не

0.06

 Learned

0.06

prend

0.06

Hol

0.06

Activations Density 0.004%

No Known Activations