INDEX

Explanations

Daniel

np_max-act · gemini-2.0-flash

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

XF

-0.08

SOC

-0.07

 πιο

-0.07

 Voyage

-0.07

ע

-0.07

-0.06

 Prest

-0.06

�

-0.06

POSITIVE LOGITS

 Daniel

0.14

Daniel

0.11

 Rachel

0.10

 Benjamin

0.10

Ben

0.09

 Samuel

0.08

 Danish

0.08

 Daniels

0.08

ben

0.08

Dan

0.08

Activations Density 0.021%

Daniel

No Comments

No Known Activations