INDEX

Explanations

in, because I could not find any connections between the MAX_ACTIVATING_TOKENS or TOP_ACTIVATING_TEXTS

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

IH

-0.07

сь

-0.06

AQ

-0.06

сть

-0.06

Vk

-0.06

启动

-0.06

 sieve

-0.06

itě

-0.06

 TARGET

-0.06

يكا

-0.05

POSITIVE LOGITS

.ErrorMessage

0.07

 MutableList

0.07

scp

0.06

้าพ

0.06

-sizing

0.06

(rotation

0.06

.DrawLine

0.06

!=

0.06

('_',

0.06

￣

0.06

Activations Density 0.609%

in, because I could not find any connections between the MAX_ACTIVATING_TOKENS or TOP_ACTIVATING_TEXTS

No Comments

No Known Activations