INDEX

Explanations

the

np_max-act · gemini-2.0-flash

The neuron detects spans of direct quotations—especially dated or cited excerpts from historical accounts.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

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

 Stan

-0.07

ateř

-0.07

/rc

-0.07

운드

-0.07

TD

-0.06

回

-0.06

Robin

-0.06

Ai

-0.06

 swell

-0.06

 Hearth

-0.06

POSITIVE LOGITS

昨

0.07

(surface

0.07

 Missile

0.06

benchmark

0.06

amental

0.06

yii

0.06

;height

0.06

enerating

0.06

 forKey

0.06

Activations Density 0.011%

the

The neuron detects spans of direct quotations—especially dated or cited excerpts from historical accounts.

No Comments

No Known Activations