© 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 · 19-RESID-POST-AA · 87773 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
87773

INDEX

Explanations

abbreviations/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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

magnitude

-0.07

(limit

-0.07

^[

-0.06

-horizontal

-0.06

งข

-0.06

(((

-0.06

Obr

-0.06

 станет

-0.06

 отнош

-0.06

+'

-0.06

POSITIVE LOGITS

sville

0.07

SEN

0.07

seen

0.07

 etmesi

0.07

isin

0.07

say

0.07

هم

0.06

سل

0.06

�

0.06

�

0.06

Activations Density 0.016%

No Known Activations