INDEX

Explanations

Data/Math/Code

np_max-act · gemini-2.0-flash

The neuron fires on numeric indices or subscripts in mathematical expressions (e.g. the “_1”, “_k”, “ldots”, “ary”, etc. in formulas).

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

variants

-0.07

.;.;

-0.07

 Yourself

-0.07

 manufacture

-0.06

έας

-0.06

months

-0.06

 Functional

-0.06

AtA

-0.06

 cutoff

-0.06

POSITIVE LOGITS

 Poke

0.07

'__

0.07

stinian

0.07

 DOCUMENT

0.07

�

0.06

 fodder

0.06

 Бі

0.06

 Sculpt

0.06

 anthrop

0.06

-request

0.06

Activations Density 0.026%

Data/Math/Code

The neuron fires on numeric indices or subscripts in mathematical expressions (e.g. the “_1”, “_k”, “ldots”, “ary”, etc. in formulas).

No Comments

No Known Activations