INDEX

Explanations

widely used

np_max-act · gemini-2.0-flash

The neuron detects phrases that describe how products are “widely used” (or similarly quantified) across various industries.

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

ござ

-0.06

人

-0.06

 deleg

-0.06

 Movie

-0.06

Ide

-0.06

cub

-0.06

未

-0.06

 Mand

-0.06

 Radeon

-0.06

Dat

-0.06

POSITIVE LOGITS

__:

0.07

 ingress

0.07

 tiến

0.07

_rights

0.07

 breaker

0.07

แบ

0.07

/back

0.07

้าค

0.06

CppTypeDefinitionSizes

0.06

VEL

0.06

Activations Density 0.021%

widely used

The neuron detects phrases that describe how products are “widely used” (or similarly quantified) across various industries.

No Comments

No Known Activations