© 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 · 7-RESID-POST-AA · 127919 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
127919

INDEX

Explanations

acetonitrile

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

_DC

-0.06

_annotations

-0.06

汗

-0.06

하는데

-0.06

 bombing

-0.06

_prop

-0.06

 Macron

-0.06

JP

-0.06

Shape

-0.06

欲

-0.06

POSITIVE LOGITS

!'↵

0.06

”)

0.06

enerating

0.06

 reinstall

0.06

 possessing

0.06

async

0.06

(inflater

0.06

thread

0.06

_visible

0.06

mith

0.06

Activations Density 0.001%

No Known Activations