INDEX

Explanations

ing

np_max-act · gemini-2.0-flash

The neuron mainly activates on gerund (“-ing”) verbs that describe ongoing actions the speaker is complaining about (e.g. “making,” “having,” “living,” “feeling”).

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

abaj

-0.06

 Light

-0.06

/back

-0.06

Sok

-0.06

ρες

-0.06

�

-0.06

";↵↵

-0.06

Reset

-0.06

_items

-0.06

 molding

-0.06

POSITIVE LOGITS

 공간

0.07

 approvals

0.07

 männ

0.07

 coordinated

0.06

ῦ

0.06

 “…

0.06

AVAILABLE

0.06

:text

0.06

xbd

0.06

 "...

0.06

Activations Density 0.027%

ing

The neuron mainly activates on gerund (“-ing”) verbs that describe ongoing actions the speaker is complaining about (e.g. “making,” “having,” “living,” “feeling”).

No Comments

No Known Activations

ing

The neuron mainly activates on gerund (“-ing”) verbs that describe ongoing actions the speaker is complaining about (e.g. “making,” “having,” “living,” “feeling”).

No Comments

No Known Activations