INDEX

Explanations

code symbols

np_max-act · gemini-2.0-flash

This neuron responds to backtick characters marking inline code spans.

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

 Cowboy

-0.07

 حي

-0.07

 deploying

-0.07

 Bakan

-0.07

viewport

-0.06

 Died

-0.06

 Pediatric

-0.06

یلی

-0.06

eb

-0.06

 ders

-0.06

POSITIVE LOGITS

iii

0.06

spect

0.06

ITER

0.06

isify

0.06

ouchers

0.06

.TYPE

0.06

Press

0.06

arel

0.06

[(

0.06

avo

0.06

Activations Density 0.028%

code symbols

This neuron responds to backtick characters marking inline code spans.

No Comments

No Known Activations