INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

This neuron detects names of keyboard keys (e.g., control and navigation keys like “escape,” “tab,” “shift,” “left,” “up,” etc.).

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

iel

-0.06

 Discrim

-0.06

肖

-0.06

цион

-0.06

owe

-0.06

("-",

-0.06

 randint

-0.06

ici

-0.06

 textarea

-0.06

nar

-0.06

POSITIVE LOGITS

 junior

0.08

ento

0.07

 fearless

0.07

geme

0.07

antidad

0.07

 없어

0.06

instagram

0.06

_step

0.06

Northern

0.06

 Marshall

0.06

Activations Density 0.002%

Code

This neuron detects names of keyboard keys (e.g., control and navigation keys like “escape,” “tab,” “shift,” “left,” “up,” etc.).

No Comments

No Known Activations