INDEX

Explanations

figure

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

^.

-0.07

 Github

-0.07

<HashMap

-0.07

Lan

-0.07

NavigationView

-0.07

 DialogResult

-0.06

 Logout

-0.06

 TreeMap

-0.06

_domains

-0.06

ivid

-0.06

POSITIVE LOGITS

qué

0.06

astro

0.06

.counter

0.06

(){}↵↵

0.06

incerely

0.06

zoek

0.06

attendance

0.06

 lawful

0.06

 phoenix

0.05

friend

0.05

Activations Density 0.002%

figure

No Comments

No Known Activations