INDEX

Explanations

amplitude

np_max-act · gemini-2.0-flash

New Auto-Interp

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 выдел

-0.07

�

-0.07

THON

-0.06

POSIT

-0.06

 easiest

-0.06

[z

-0.06

coc

-0.06

 predatory

-0.06

 coastline

-0.06

 التس

-0.06

POSITIVE LOGITS

 amplitude

0.11

plitude

0.09

 magnitude

0.09

Magnitude

0.08

 Blade

0.07

erture

0.06

ulse

0.06

magnitude

0.06

(FLAGS

0.06

 meydana

0.06

Activations Density 0.006%

amplitude

No Comments

No Known Activations