INDEX

Explanations

company rankings and awards

np_max-act · gemini-2.0-flash

The neuron detects mentions of awards, recognitions, and accolade-related terms.

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

 Jerseys

-0.07

 शर

-0.07

 operatives

-0.07

people

-0.06

uede

-0.06

 cumshot

-0.06

STEP

-0.06

 Schwartz

-0.06

 Darling

-0.06

 öden

-0.06

POSITIVE LOGITS

:selected

0.07

etAddress

0.06

لسل

0.06

DIS

0.06

 τις

0.06

 направ

0.06

obble

0.06

 haul

0.06

 XmlNode

0.06

 tracer

0.06

Activations Density 0.014%

company rankings and awards

The neuron detects mentions of awards, recognitions, and accolade-related terms.

No Comments

No Known Activations