INDEX

Explanations

programming structures

np_max-act · gemini-2.0-flash

The neuron activates on mentions of data‐structure or type definitions (e.g. “struct,” “estructura,” “typedef,” etc.).

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

Hy

-0.07

غيل

-0.06

argest

-0.06

 fraud

-0.06

%x

-0.06

swe

-0.06

.status

-0.06

 shipped

-0.06

srv

-0.06

okus

-0.06

POSITIVE LOGITS

 Represent

0.07

,proto

0.07

 вообще

0.07

 chương

0.07

 numberOfRowsInSection

0.07

 благодаря

0.07

 FileNotFoundError

0.07

 serializers

0.06

lifetime

0.06

 الحل

0.06

Activations Density 0.043%

programming structures

The neuron activates on mentions of data‐structure or type definitions (e.g. “struct,” “estructura,” “typedef,” etc.).

No Comments

No Known Activations