© 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 · 35705 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
35705

INDEX

Explanations

Japanese

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

 trois

-0.07

 Kabul

-0.06

.Gravity

-0.06

Ric

-0.06

ascar

-0.06

 которым

-0.06

 багатьох

-0.06

 Divider

-0.06

ζί

-0.06

 Maui

-0.06

POSITIVE LOGITS

ayı

0.07

 Amazing

0.06

 показ

0.06

).(

0.06

Gesture

0.06

_↵

0.06

OPEN

0.06

⟩

0.06

 ejemplo

0.06

 зада

0.06

Activations Density 0.004%

No Known Activations