INDEX

Explanations

code, data structures

np_max-act · gemini-2.0-flash

The neuron responds to numeric literals in code, especially floating-point numbers.

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

�

-0.07

(msg

-0.07

	process

-0.06

 booklet

-0.06

src

-0.06

 torture

-0.06

FIXME

-0.06

 keinen

-0.06

цвет

-0.06

implicit

-0.06

POSITIVE LOGITS

()")↵

0.07

'}↵↵

0.06

การแข

0.06

 nové

0.06

 Kitty

0.06

 gön

0.06

。

0.06

.QRect

0.06

ivery

0.06

파

0.06

Activations Density 0.020%

code, data structures

The neuron responds to numeric literals in code, especially floating-point numbers.

No Comments

No Known Activations