INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

The neuron responds to programming‐language type and template syntax (e.g. C/C++ type names, angle brackets, pointers, and template token constructs).

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

burgh

-0.07

 họp

-0.07

्रय

-0.07

ксп

-0.06

 spared

-0.06

ры

-0.06

반기

-0.06

 Preferences

-0.06

dehy

-0.06

enburg

-0.06

POSITIVE LOGITS

 (↵

0.07

trusted

0.07

pick

0.06

")){
↵

0.06

 ()=>{↵

0.06

!!}</

0.06

 textColor

0.06

�

0.06

vfs

0.06

Alex

0.06

Activations Density 0.192%

punctuation

The neuron responds to programming‐language type and template syntax (e.g. C/C++ type names, angle brackets, pointers, and template token constructs).

No Comments

No Known Activations