INDEX

Explanations

center

np_max-act · gemini-2.0-flash

The neuron activates on CSS “align-items” flexbox alignment rules.

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

again

-0.07

Když

-0.07

衣服

-0.06

-issue

-0.06

 Lies

-0.06

 Followers

-0.06

 pytest

-0.06

 vanish

-0.06

].[

-0.06

 five

-0.06

POSITIVE LOGITS

 Easily

0.07

StartTime

0.07

 pick

0.06

 lineman

0.06

uously

0.06

Callback

0.06

 twitch

0.06

zone

0.06

retry

0.06

нд

0.06

Activations Density 0.001%

center

The neuron activates on CSS “align-items” flexbox alignment rules.

No Comments

No Known Activations