INDEX

Explanations

code, programming

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of “Split” method calls (e.g. Regex.Split or String.Split).

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

bil

-0.07

_cod

-0.07

.OK

-0.07

-cost

-0.07

 rallied

-0.07

 daily

-0.07

 fascinated

-0.06

Face

-0.06

Instructions

-0.06

POSITIVE LOGITS

 hyperlink

0.06

.createClass

0.06

(sprite

0.06

 dokon

0.06

 Thema

0.06

лем

0.06

�

0.06

/component

0.06

(lo

0.06

 электрон

0.06

Activations Density 0.077%

code, programming

The neuron fires on occurrences of “Split” method calls (e.g. Regex.Split or String.Split).

No Comments

No Known Activations