INDEX

Explanations

character/characters

np_max-act · gemini-2.0-flash

the product name and its key features or specifications.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron activates on numeric specifications and measurement terms (e.g. counts of “characters,” numerical limits, units).

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

这

-0.07

़

-0.06

お

-0.06

ui

-0.06

 literature

-0.06

Bow

-0.06

 plantation

-0.06

、お

-0.06

utting

-0.06

 Armenian

-0.06

POSITIVE LOGITS

.code

0.07

 complexity

0.07

NOI

0.07

 Callable

0.06

 Dont

0.06

 Compiled

0.06

 detainees

0.06

 Cursor

0.06

ifference

0.06

Activations Density 0.003%

character/characters

the product name and its key features or specifications.

The neuron activates on numeric specifications and measurement terms (e.g. counts of “characters,” numerical limits, units).

No Comments

No Known Activations