INDEX

Explanations

purchases

np_max-act · gemini-2.0-flash

The neuron detects mentions of purchasing a car.

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

 movie

-0.07

AKE

-0.07

	text

-0.06

NE

-0.06

Boston

-0.06

 Mothers

-0.06

.pe

-0.06

�

-0.06

 obstruct

-0.06

 frozen

-0.06

POSITIVE LOGITS

exao

0.07

_CH

0.06

 Голов

0.06

ISTA

0.06

흐

0.06

ázky

0.06

níku

0.06

τών

0.06

arDown

0.06

 hakkı

0.06

Activations Density 0.101%

purchases

The neuron detects mentions of purchasing a car.

No Comments

No Known Activations