INDEX

Explanations

Formal/mathematical language

np_max-act · gemini-2.0-flash

This neuron activates on numeric literals written as decimal (floating‐point) numbers.

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

ọ

-0.07

pression

-0.07

Stencil

-0.06

 hanya

-0.06

.Initial

-0.06

 dancer

-0.06

gun

-0.06

ornment

-0.06

(userData

-0.06

_SLEEP

-0.06

POSITIVE LOGITS

 Tories

0.07

=======

0.06

 possibilities

0.06

.gridy

0.06

"{"

0.06

iktig

0.06

 utter

0.06

 Sist

0.06

)==

0.06

ERNEL

0.06

Activations Density 0.025%

Formal/mathematical language

This neuron activates on numeric literals written as decimal (floating‐point) numbers.

No Comments

No Known Activations