INDEX

Explanations

food

np_max-act · gemini-2.0-flash

The main thing this neuron does is detect mentions of food and culinary–related terms.

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

人才

-0.07

 glGen

-0.06

 güçlü

-0.06

.HasPrefix

-0.06

 validate

-0.06

------+

-0.06

flash

-0.06

dız

-0.06

ido

-0.06

Una

-0.06

POSITIVE LOGITS

AJOR

0.06

NRA

0.06

ieder

0.06

 каф

0.06

~~

0.06

Cheers

0.06

ốc

0.06

 Anthony

0.06

 xAxis

0.06

 Coord

0.06

Activations Density 0.023%

food

The main thing this neuron does is detect mentions of food and culinary–related terms.

No Comments

No Known Activations

food

The main thing this neuron does is detect mentions of food and culinary–related terms.

No Comments

No Known Activations