INDEX

Explanations

Scientific research

np_max-act · gemini-2.0-flash

The neuron specializes in spotting descriptions of experimental assays and measurement results (e.g. “tested for,” “production of,” “ability to,” “characterized by”) in scientific texts.

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

Moment

-0.06

osex

-0.06

Raises

-0.06

敦

-0.06

 concatenated

-0.06

degree

-0.06

remainder

-0.06

Those

-0.06

ラン

-0.06

 Jako

-0.06

POSITIVE LOGITS

 strokeLine

0.07

 dint

0.07

إ

0.07

 Autos

0.06

(nr

0.06

 tisí

0.06

(tcp

0.06

 aplic

0.06

("+

0.06

irket

0.06

Activations Density 0.019%

Scientific research

The neuron specializes in spotting descriptions of experimental assays and measurement results (e.g. “tested for,” “production of,” “ability to,” “characterized by”) in scientific texts.

No Comments

No Known Activations

Scientific research

The neuron specializes in spotting descriptions of experimental assays and measurement results (e.g. “tested for,” “production of,” “ability to,” “characterized by”) in scientific texts.

No Comments

No Known Activations