© 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 · 15-RESID-POST-AA · 75429 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
75429

INDEX

Explanations

Code/Data structures

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

-cost

-0.07

ło

-0.07

 unusual

-0.06

Mi

-0.06

trainer

-0.06

 Conrad

-0.06

stu

-0.06

 textiles

-0.06

„A

-0.06

(always

-0.06

POSITIVE LOGITS

_ALIGN

0.07

 humanoid

0.07

.Highlight

0.06

ाफ

0.06

RESET

0.06

 Wifi

0.06

 sooner

0.06

|^

0.06

 EventHandler

0.06

ivial

0.06

Activations Density 0.000%

No Known Activations