INDEX

Explanations

periods

np_max-act · gemini-2.0-flash

The neuron activates on tennis match result lines, identifying the score‐reporting pattern (e.g. sets and tiebreak scores).

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

 embodiments

-0.07

={<

-0.06

=status

-0.06

 Chair

-0.06

ynamic

-0.06

-prev

-0.06

(async

-0.06

 ninh

-0.06

 сосед

-0.06

 Innovation

-0.06

POSITIVE LOGITS

ust

0.07

 Vish

0.06

 стены

0.06

sc

0.06

_GUID

0.06

 Aurora

0.06

 authDomain

0.06

 graduates

0.06

 tutoring

0.06

[])↵

0.06

Activations Density 0.007%

periods

The neuron activates on tennis match result lines, identifying the score‐reporting pattern (e.g. sets and tiebreak scores).

No Comments

No Known Activations