INDEX

Explanations

"Olm" names and places

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

'é

-0.07

 helps

-0.07

mx

-0.07

str

-0.06

 seek

-0.06

 thread

-0.06

obuf

-0.06

Extract

-0.06

१९

-0.06

	long

-0.06

POSITIVE LOGITS

locked

0.08

ipeg

0.07

ufact

0.07

 Mattis

0.07

lun

0.07

ليم

0.06

ATT

0.06

(separator

0.06

alore

0.06

 grassroots

0.06

Activations Density 0.006%

"Olm" names and places

No Comments

No Known Activations