INDEX

Explanations

}

np_max-act · gemini-2.0-flash

This neuron detects floating‐point numeric values (decimal numbers) in section headings or measurement contexts.

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

 Ferry

-0.06

 prolific

-0.06

 lack

-0.06

 circuits

-0.06

 Jacques

-0.06

 abortion

-0.06

FFFF

-0.06

كي

-0.06

 Kushner

-0.06

reu

-0.06

POSITIVE LOGITS

 bergen

0.07

 chấm

0.07

 đào

0.06

履

0.06

 WebGL

0.06

.reloadData

0.06

 wasm

0.06

 glGet

0.06

rika

0.06

.erase

0.06

Activations Density 0.003%

}

This neuron detects floating‐point numeric values (decimal numbers) in section headings or measurement contexts.

No Comments

No Known Activations

}

This neuron detects floating‐point numeric values (decimal numbers) in section headings or measurement contexts.

No Comments

No Known Activations