INDEX

Explanations

file

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of the word “file” (and its variants like “files” or “filing”).

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

 defenders

-0.07

 serpent

-0.07

 animals

-0.07

 Moment

-0.06

 autumn

-0.06

 мужчин

-0.06

akah

-0.06

ociety

-0.06

 Georgetown

-0.06

ORD

-0.06

POSITIVE LOGITS

 File

0.08

 dossier

0.08

 usern

0.07

))

0.07

assign

0.07

 files

0.07

cheme

0.07

 fileId

0.07

 filesystem

0.07

 FILES

0.07

Activations Density 0.008%

file

The neuron activates on occurrences of the word “file” (and its variants like “files” or “filing”).

No Comments

No Known Activations