INDEX

Explanations

Business and economics

np_max-act · gemini-2.0-flash

The neuron activates on language that frames things as a “smart,” “economic,” or “business” choice—i.e. pragmatic or monetary-incentive arguments.

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

Cancellation

-0.08

 incre

-0.07

 onun

-0.06

uania

-0.06

 během

-0.06

 نگهد

-0.06

τεύ

-0.06

Sq

-0.06

 scissors

-0.06

 результате

-0.06

POSITIVE LOGITS

spec

0.07

Fig

0.07

 vivid

0.06

 hardest

0.06

download

0.06

'{

0.06

CAN

0.06

 investigates

0.06

namen

0.06

esses

0.06

Activations Density 0.079%

Business and economics

The neuron activates on language that frames things as a “smart,” “economic,” or “business” choice—i.e. pragmatic or monetary-incentive arguments.

No Comments

No Known Activations