© 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 · 91047 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
7-RESID-POST-AA
91047

INDEX

Explanations

knowledge

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

.AppendText

-0.07

.WebServlet

-0.06

buff

-0.06

heg

-0.06

SetText

-0.06

Ble

-0.06

 transl

-0.06

 Kernel

-0.06

IFO

-0.06

 Ethan

-0.06

POSITIVE LOGITS

sis

0.07

="""

0.07

 jazy

0.07

naj

0.07

ega

0.07

Při

0.06

FRINGEMENT

0.06

 korun

0.06

/news

0.06

вещ

0.06

Activations Density 0.018%

No Known Activations