INDEX

Explanations

Earth

np_max-act · gemini-2.0-flash

The neuron is triggered by mentions of Earth’s “-sphere” terms (especially “biosphere,” but also hydrosphere/atmosphere‐style words).

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

.exec

-0.06

SCALE

-0.06

UMP

-0.06

olan

-0.06

five

-0.06

.Valid

-0.06

 Egypt

-0.06

 Gordon

-0.06

Buffer

-0.06

 newer

-0.06

POSITIVE LOGITS

[unit

0.07

ليم

0.06

 componentDid

0.06

 жир

0.06

�

0.06

 Entered

0.06

stay

0.06

_WINDOWS

0.06

 dial

0.06

 listOf

0.06

Activations Density 0.022%

Earth

The neuron is triggered by mentions of Earth’s “-sphere” terms (especially “biosphere,” but also hydrosphere/atmosphere‐style words).

No Comments

No Known Activations