INDEX

Explanations

changes from a past state

np_max-act · gemini-2.0-flash

This neuron lights up on first‐person “I” statements—tokens like “I,” “Now I,” or “I have/created/am trying” that introduce the author’s actions.

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

ismatic

-0.07

suma

-0.06

cin

-0.06

 cortical

-0.06

<!--<

-0.06

 coaster

-0.06

 passes

-0.06

).'</

-0.06

oba

-0.06

 PLAN

-0.06

POSITIVE LOGITS

タイプ

0.08

ori

0.08

,result

0.07

.land

0.07

 Під

0.06

 рекоменда

0.06

�

0.06

	Return

0.06

 एज

0.06

 ще

0.06

Activations Density 0.103%

changes from a past state

This neuron lights up on first‐person “I” statements—tokens like “I,” “Now I,” or “I have/created/am trying” that introduce the author’s actions.

No Comments

No Known Activations

changes from a past state

This neuron lights up on first‐person “I” statements—tokens like “I,” “Now I,” or “I have/created/am trying” that introduce the author’s actions.

No Comments

No Known Activations