© 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 · 17521 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
17521

INDEX

Explanations

as

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

具体

-0.07

veç

-0.07

olm

-0.07

 /*!<

-0.07

 sach

-0.06

don

-0.06

 وسی

-0.06

 cutoff

-0.06

ढ़

-0.06

 tiế

-0.06

POSITIVE LOGITS

 graduate

0.07

imoto

0.06

classList

0.06

We

0.06

 dříve

0.06

 programma

0.06

PE

0.06

 JpaRepository

0.06

 tenants

0.06

.classList

0.06

Activations Density 0.011%

No Known Activations