INDEX

Explanations

split

np_max-act · gemini-2.0-flash

The neuron primarily fires on occurrences of the token “split,” i.e. calls to the split method.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Rank

-0.09

	score

-0.07

 explanations

-0.06

 through

-0.06

 gode

-0.06

/she

-0.06

 focused

-0.06

яд

-0.06

 adequate

-0.06

-sharing

-0.06

POSITIVE LOGITS

爾

0.07

 mekt

0.07

 держави

0.07

_ACTIV

0.06

_svc

0.06

*a

0.06

 imread

0.06

CWE

0.06

.xpath

0.06

 Rentals

0.06

Activations Density 0.004%

split

The neuron primarily fires on occurrences of the token “split,” i.e. calls to the split method.

No Comments

No Known Activations