INDEX

Explanations

electrode

np_max-act · gemini-2.0-flash

The neuron detects occurrences of the term “electrode” (and closely related forms) in technical descriptions.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

ビ

-0.07

 ling

-0.07

-parse

-0.07

 nature

-0.06

|max

-0.06

in

-0.06

.Min

-0.06

POSITIVE LOGITS

 electrodes

0.14

 electrode

0.13

 extreme

0.07

{EIF

0.07

лось

0.07

ioned

0.07

 تأثیر

0.07

 UserController

0.07

interested

0.07

pseudo

0.07

Activations Density 0.004%

electrode

The neuron detects occurrences of the term “electrode” (and closely related forms) in technical descriptions.

No Comments

No Known Activations