INDEX

Explanations

math notation

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

 Intellectual

-0.08

Tele

-0.07

 eviction

-0.07

_latest

-0.07

least

-0.07

 Jennifer

-0.07

 intellectual

-0.07

 enactment

-0.07

^(

-0.07

 Caucasian

-0.07

POSITIVE LOGITS

(node

0.07

 tailored

0.07

При

0.06

 budete

0.06

aqu

0.06

 řid

0.06

	Command

0.06

erties

0.06

emas

0.06

+"/

0.06

Activations Density 0.016%

math notation

No Comments

No Known Activations