© 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 · 9490 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
9490

INDEX

Explanations

numpy

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

Tokenizer

-0.07

Vel

-0.07

Section

-0.07

дел

-0.07

Mag

-0.07

 uptake

-0.07

plt

-0.06

 ideological

-0.06

_category

-0.06

Topics

-0.06

POSITIVE LOGITS

 své

0.07

 numpy

0.06

иск

0.06

 Hyderabad

0.06

确认

0.06

 Russian

0.06

 日本

0.06

 Simple

0.06

預

0.06

(EXIT

0.06

Activations Density 0.005%

No Known Activations