INDEX

Explanations

Dates and spans of time

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

 Luxury

-0.06

rylic

-0.06

IVITY

-0.06

.resize

-0.06

 Guarantee

-0.06

 shrimp

-0.06

ptide

-0.06

Cells

-0.06

	Path

-0.05

 Path

-0.05

POSITIVE LOGITS

 แหล

0.06

/ap

0.06

ρθ

0.06

akukan

0.06

sexual

0.06

.SQLException

0.06

abras

0.06

autoload

0.06

.getenv

0.06

 stores

0.06

Activations Density 0.102%

Dates and spans of time

No Comments

No Known Activations