INDEX

Explanations

Chemicals and artificial additives in food

np_max-act · gemini-2.0-flash

The neuron flags mentions of chemical or additive ingredients (e.g., “chemicals,” “additives,” “preservatives,” “artificial,” etc.).

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

-0.07

bp

-0.06

努

-0.06

.COM

-0.06

 nắm

-0.06

쓰

-0.06

 тов

-0.06

_extended

-0.06

cancel

-0.06

POSITIVE LOGITS

 Federal

0.07

 groin

0.07

_failed

0.07

 Teaching

0.06

 gider

0.06

/"↵

0.06

 Americans

0.06

 evangelical

0.06

 heavier

0.06

 Martin

0.06

Activations Density 0.017%

Chemicals and artificial additives in food

The neuron flags mentions of chemical or additive ingredients (e.g., “chemicals,” “additives,” “preservatives,” “artificial,” etc.).

No Comments

No Known Activations