INDEX

Explanations

hair

np_max-act · gemini-2.0-flash

The neuron activates on hair-related terms (e.g. “hair,” “hair-do,” “hair dryer,” “brush”).

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

	volatile

-0.07

-zone

-0.07

ưng

-0.07

respond

-0.07

Pty

-0.07

 evangel

-0.06

つぶ

-0.06

ampion

-0.06

 monk

-0.06

POSITIVE LOGITS

 hair

0.20

 Hair

0.16

Hair

0.13

air

0.08

hair

0.08

 hairs

0.08

 Barber

0.08

 hairy

0.08

 hairst

0.07

Hir

0.07

Activations Density 0.010%

hair

The neuron activates on hair-related terms (e.g. “hair,” “hair-do,” “hair dryer,” “brush”).

No Comments

No Known Activations

hair

The neuron activates on hair-related terms (e.g. “hair,” “hair-do,” “hair dryer,” “brush”).

No Comments

No Known Activations