INDEX

Explanations

Do it yourself

np_max-act · gemini-2.0-flash

The neuron fires on second-person address and advice language—words like “you,” “own,” “try,” “tackle,” and other cues that the text is giving instructions or directions to the reader.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

references to DIY/self-performed repairs or treatments—especially warnings not to “try it yourself” and to call a professional instead.

oai_token-act-pair · gpt-5 Triggered by @vetterc0

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

endment

-0.07

服務

-0.06

 story

-0.06

 설정

-0.06

pike

-0.06

 request

-0.06

Dialogue

-0.06

utto

-0.06

uggy

-0.06

 guilt

-0.06

POSITIVE LOGITS

 sondern

0.07

dap

0.06

exp

0.06

.correct

0.06

 Zend

0.06

 přičemž

0.06

 قائمة

0.06

Pes

0.06

 redu

0.06

 additionally

0.06

Activations Density 0.084%

Do it yourself

The neuron fires on second-person address and advice language—words like “you,” “own,” “try,” “tackle,” and other cues that the text is giving instructions or directions to the reader.

references to DIY/self-performed repairs or treatments—especially warnings not to “try it yourself” and to call a professional instead.

No Comments

No Known Activations

Do it yourself

The neuron fires on second-person address and advice language—words like “you,” “own,” “try,” “tackle,” and other cues that the text is giving instructions or directions to the reader.

references to DIY/self-performed repairs or treatments—especially warnings not to “try it yourself” and to call a professional instead.

No Comments

No Known Activations