INDEX

Explanations

adaptive

np_max-act · gemini-2.0-flash

The neuron detects occurrences of the word “adaptive.”

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

군

-0.07

 translated

-0.07

istr

-0.07

 нез

-0.06

 numbering

-0.06

run

-0.06

())))↵

-0.06

 Elect

-0.06

 Johnson

-0.06

POSITIVE LOGITS

 Adaptive

0.11

 adaptive

0.10

adaptive

0.08

APA

0.07

ATP

0.07

档

0.07

 लड

0.07

 độ

0.07

 estimating

0.07

캐

0.07

Activations Density 0.002%

adaptive

The neuron detects occurrences of the word “adaptive.”

No Comments

No Known Activations