© 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 · 23-RESID-POST-AA · 101520 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
23-RESID-POST-AA
101520

INDEX

Explanations

Account status/compromise

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

आ

-0.07

	admin

-0.07

极

-0.06

约

-0.06

-0.06

ited

-0.06

 intervened

-0.06

dok

-0.06

 involving

-0.06

 sona

-0.06

POSITIVE LOGITS

nitř

0.07

RESULT

0.07

 محل

0.06

auled

0.06

qty

0.06

 yaşan

0.06

/new

0.06

extends

0.06

emen

0.06

 SPDX

0.06

Activations Density 0.030%

No Known Activations