INDEX

Explanations

adaptive

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

 ctor

-0.07

'!

-0.07

StyleSheet

-0.07

 Bond

-0.06

 Casino

-0.06

 Market

-0.06

--------------↵

-0.06

 wished

-0.06

’t

-0.06

 August

-0.06

POSITIVE LOGITS

 resend

0.06

altimore

0.06

 Adaptive

0.06

flammatory

0.06

 adap

0.06

apsible

0.06

-install

0.06

-loaded

0.06

wide

0.06

Activations Density 0.002%

adaptive

No Comments

No Known Activations