INDEX

Explanations

increasing difficulty

np_max-act · gemini-2.0-flash

The neuron flags floating‐point number literals (decimal values) in the text.

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

.Keyboard

-0.07

rick

-0.07

 wand

-0.06

 TextEditingController

-0.06

 ков

-0.06

gcd

-0.06

 fenced

-0.06

oystick

-0.06

 мало

-0.06

 camar

-0.06

POSITIVE LOGITS

 člán

0.07

_uint

0.07

=”

0.07

angler

0.06

ipsis

0.06

θο

0.06

ように

0.06

-desktop

0.06

 Европ

0.06

 สพป

0.06

Activations Density 0.009%

increasing difficulty

The neuron flags floating‐point number literals (decimal values) in the text.

No Comments

No Known Activations

increasing difficulty

The neuron flags floating‐point number literals (decimal values) in the text.

No Comments

No Known Activations