INDEX

Explanations

grow

np_max-act · gemini-2.0-flash

The neuron detects mentions of microbial growth, specifically occurrences of “grow” or “growth.”

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

_chr

-0.07

 EXCEPTION

-0.07

 langu

-0.07

버

-0.07

 notions

-0.07

archive

-0.06

Nab

-0.06

.Prop

-0.06

JECTED

-0.06

POSITIVE LOGITS

 resultList

0.06

(off

0.06

 intervening

0.06

 Convenience

0.06

inciple

0.06

？”

0.06

SED

0.06

Suz

0.06

nox

0.06

gro

0.06

Activations Density 0.011%

grow

The neuron detects mentions of microbial growth, specifically occurrences of “grow” or “growth.”

No Comments

No Known Activations