INDEX

Explanations

First-person writing

np_max-act · gemini-2.0-flash

The neuron flags first‐person expressions of personal need or obligation (e.g. “I need to …”).

oai_token-act-pair · o4-mini

Triggered by @xinyanhu8

first-person personal statements or requests (utterances beginning with "I" describing personal situation or asking for help).

oai_token-act-pair · gpt-5-mini

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

Negative Logits

ırı

-0.06

aybe

-0.06

 пост

-0.06

Creative

-0.06

Playable

-0.06

sect

-0.06

ену

-0.06

 пом

-0.06

ds

-0.06

جب

-0.06

POSITIVE LOGITS

_AHB

0.07

technical

0.07

.contentMode

0.07

ORG

0.06

Ś

0.06

hd

0.06

 πο

0.06

fox

0.06

 ε�

0.06

پ

0.06

Activations Density 0.116%

First-person writing

The neuron flags first‐person expressions of personal need or obligation (e.g. “I need to …”).

first-person personal statements or requests (utterances beginning with "I" describing personal situation or asking for help).

No Known Activations

First-person writing

The neuron flags first‐person expressions of personal need or obligation (e.g. “I need to …”).

first-person personal statements or requests (utterances beginning with "I" describing personal situation or asking for help).

No Known Activations