INDEX

Explanations

constraints, math formulas

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

 lavoro

-0.07

 نقاط

-0.07

ΕΝ

-0.07

 BoxFit

-0.07

 forCellReuseIdentifier

-0.06

'order

-0.06

ebiliriz

-0.06

 пти

-0.06

\Container

-0.06

POSITIVE LOGITS

 empowering

0.07

registry

0.06

 shopping

0.06

 woodworking

0.06

 entering

0.06

staking

0.06

 becoming

0.06

 userId

0.06

_each

0.06

Activations Density 0.006%

constraints, math formulas

No Comments

No Known Activations