© 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 · 106564 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
106564

INDEX

Explanations

/kg

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

 нор

-0.06

ّل

-0.06

	Long

-0.06

]=='

-0.06

 Benchmark

-0.06

ChangeEvent

-0.06

projection

-0.06

ロー

-0.06

-exec

-0.06

.getEntity

-0.06

POSITIVE LOGITS

Legend

0.07

승

0.06

(w

0.06

 Ост

0.06

:::

0.06

 tends

0.06

ax

0.06

Vij

0.06

_end

0.06

 """↵↵

0.06

Activations Density 0.000%

No Known Activations