INDEX

Explanations

digestive

np_max-act · gemini-2.0-flash

This neuron detects mentions of digestion or the digestive system.

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

-0.06

 Kenny

-0.06

 Shed

-0.06

ах

-0.06

 Kara

-0.06

nst

-0.06

uminum

-0.06

 nineteen

-0.06

 strs

-0.06

.Position

-0.06

POSITIVE LOGITS

 digestion

0.09

 digestive

0.08

Expressions

0.07

 digest

0.07

 progressive

0.07

 hubby

0.07

�

0.07

 lover

0.06

°}

0.06

σί

0.06

Activations Density 0.003%

digestive

This neuron detects mentions of digestion or the digestive system.

No Comments

No Known Activations