© 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 · 11-RESID-POST-AA · 74818 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
74818

INDEX

Explanations

ation

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

Say

-0.07

Ping

-0.07

SMS

-0.07

OVID

-0.06

-return

-0.06

 evid

-0.06

Instant

-0.06

<Result

-0.06

pdf

-0.06

 conver

-0.06

POSITIVE LOGITS

axe

0.07

_sha

0.06

áb

0.06

_RED

0.06

 tạm

0.06

 düzenlem

0.06

zal

0.06

 вк

0.06

 DataColumn

0.06

zą

0.06

Activations Density 0.015%

No Known Activations