© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

LLAMA3.1-8B-IT · 15-RESID-POST-AA · 33184 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
33184

INDEX

Explanations

fire

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

 گیری

-0.07

 WHILE

-0.07

Agregar

-0.06

 reass

-0.06

อล

-0.06

<=

-0.06

 Produto

-0.06

SUCCESS

-0.06

(section

-0.06

(Unit

-0.06

POSITIVE LOGITS

boxed

0.07

/rand

0.06

 forestry

0.06

 Emmanuel

0.06

athon

0.06

va

0.06

_Part

0.06

zu

0.06

вет

0.06

nn

0.06

Activations Density 0.000%

No Known Activations