© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 19-RESID-POST-AA · 92263 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
19-RESID-POST-AA
92263

INDEX

Explanations

Premium

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

 flaw

-0.07

>t

-0.07

-0.06

 avoir

-0.06

 Conflict

-0.06

_estimate

-0.06

--------------

-0.06

 mice

-0.06

 همکاری

-0.06

 lays

-0.06

POSITIVE LOGITS

premium

0.09

Premium

0.09

 Premium

0.08

 premium

0.08

 quảng

0.07

قات

0.07

 oranı

0.07

扣

0.07

±ط

0.07

 prestige

0.07

Activations Density 0.003%

No Known Activations