INDEX

Explanations

real-world studies

np_max-act · gemini-2.0-flash

This neuron detects mentions of real-world or field conditions (e.g., “natural,” “real,” “in situ,” “field”) as opposed to controlled or laboratory settings.

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

 Skinner

-0.07

 невозможно

-0.06

需求

-0.06

ため

-0.06

處

-0.06

 Cree

-0.06

_pre

-0.06

overlay

-0.06

 insect

-0.06

POSITIVE LOGITS

([{

0.07

 вони

0.06

ing

0.06

 turkey

0.06

gaz

0.06

اضي

0.06

 contentType

0.06

 Fraction

0.06

_MATH

0.06

ailing

0.06

Activations Density 0.058%

real-world studies

This neuron detects mentions of real-world or field conditions (e.g., “natural,” “real,” “in situ,” “field”) as opposed to controlled or laboratory settings.

No Comments

No Known Activations