INDEX

Explanations

allowed

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Bethesda

-0.07

 savings

-0.07

 Text

-0.06

 capital

-0.06

 scri

-0.06

Ví

-0.06

Tai

-0.06

상

-0.06

 Conversion

-0.06

POSITIVE LOGITS

 allowed

0.12

 permitted

0.09

 Allowed

0.08

 ALLOW

0.07

 allowable

0.07

 경우

0.07

 loose

0.07

 shall

0.07

allowed

0.07

.member

0.06

Activations Density 0.010%

allowed

No Comments

No Known Activations