INDEX

Explanations

programming

np_max-act · gemini-2.0-flash

This neuron detects API documentation element labels—tokens like “Method,” “Class,” “Property,” or “Structure” in headings.

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

 společnosti

-0.07

 Gratis

-0.07

ores

-0.07

alten

-0.06

robat

-0.06

istrator

-0.06

udiante

-0.06

ovo

-0.06

!»

-0.06

 Erik

-0.06

POSITIVE LOGITS

 seizures

0.07

-da

0.06

loff

0.06

rg

0.06

toInt

0.06

(EIF

0.06

 발견

0.06

 Rail

0.06

'=

0.06

ánt

0.05

Activations Density 0.011%

programming

This neuron detects API documentation element labels—tokens like “Method,” “Class,” “Property,” or “Structure” in headings.

No Comments

No Known Activations