INDEX

Explanations

linked lists

np_max-act · gemini-2.0-flash

The neuron fires on code tokens that manipulate linked-list pointers—especially accesses or assignments to fields like head, tail, next, and prev.

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

認

-0.07

 campground

-0.06

IGGER

-0.06

 RegExp

-0.06

ег

-0.06

 grandmother

-0.06

enha

-0.06

 Pří

-0.06

Called

-0.06

OLVE

-0.06

POSITIVE LOGITS

rm

0.07

uc

0.07

 下跌

0.07

 кот

0.07

 jíd

0.07

|^

0.06

_tran

0.06

 ем

0.06

剑

0.06

İh

0.06

Activations Density 0.006%

linked lists

The neuron fires on code tokens that manipulate linked-list pointers—especially accesses or assignments to fields like head, tail, next, and prev.

No Comments

No Known Activations