INDEX

Explanations

code snippets

np_max-act · gemini-2.0-flash

The neuron fires on tokens that name or refer to a “second” data‐frame (or similarly suffixed data‐object), e.g. numeric suffixes like “2” in “df2” or “data_frame_2.”

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

-0.06

_elements

-0.06

 Hoffman

-0.06

 restarting

-0.06

Dallas

-0.06

-flight

-0.06

obox

-0.06

ohan

-0.06

=";↵

-0.06

 alleles

-0.06

POSITIVE LOGITS

))*

0.07

 dati

0.06

_tC

0.06

UREMENT

0.06

niž

0.06

 عرض

0.06

 supernatural

0.06

 Certified

0.06

 deactivated

0.06

 genre

0.06

Activations Density 0.069%

code snippets

The neuron fires on tokens that name or refer to a “second” data‐frame (or similarly suffixed data‐object), e.g. numeric suffixes like “2” in “df2” or “data_frame_2.”

No Comments

No Known Activations

code snippets

The neuron fires on tokens that name or refer to a “second” data‐frame (or similarly suffixed data‐object), e.g. numeric suffixes like “2” in “df2” or “data_frame_2.”

No Comments

No Known Activations