© 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 · 15-RESID-POST-AA · 20313 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
20313

INDEX

Explanations

.NoError

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

 detain

-0.07

chars

-0.07

ülebilir

-0.06

 Moodle

-0.06

.Foundation

-0.06

(viewModel

-0.06

[curr

-0.06

Uniform

-0.06

 дра

-0.06

 MESSAGE

-0.06

POSITIVE LOGITS

 afford

0.07

زل

0.06

레

0.06

Ensure

0.06

yu

0.06

丈

0.06

eee

0.06

_SCOPE

0.06

 gehen

0.06

 вказ

0.06

Activations Density 0.003%

No Known Activations