INDEX

Explanations

Updates and further information

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 depict

-0.07

 anche

-0.07

 Tick

-0.07

隊

-0.06

 seventy

-0.06

 conced

-0.06

 budete

-0.06

vailable

-0.06

 smoothly

-0.06

POSITIVE LOGITS

=C

0.07

_FILENO

0.07

(encoder

0.06

 rais

0.06

 Toggle

0.06

老

0.06

_region

0.06

igaret

0.06

pletion

0.06

Activations Density 0.013%

Updates and further information

No Comments

No Known Activations