pressure
Datasets
All datasets matching “pressure”SeasonBench-EA-METEO_FRANCE-PressureThe dataset is a subset for SeasonBench-EA Benchmark, which contains the ensemble forecasts from Meteo France on pressure levels. All data are downloaded from the Copernicus Climate Data Store (https://cds.climate.copernicus.eu/) and reorganized for benchmark construction. Please ensure compliance with the CDS Licence when using or redistributing the data.
tigge-cf-pressure
TIGGE Control Forecasts — pressure levels, 1.5°
An automated, growing archive of TIGGE control forecasts (cf) on pressure levels, regridded
to 1.5°, from ECMWF, NCEP, and CMA, retrieved from the ECMWF Data Store (ECDS)
tigge-forecasts collection.
Contents
Centres
ECMWF, NCEP, CMA
Forecast type
control forecast (cf) only
Variables
geopotential height, temperature, specific humidity, u-wind, v-wind
Pressure levels
1000, 925, 850, 700, 500, 300… See the full description on the dataset page: https://huggingface.co/datasets/yanxingjianken/tigge-cf-pressure.SeasonBench-EA-ECMWF-PressureThe dataset is a subset for SeasonBench-EA Benchmark, which contains the ensemble forecasts from ECMWF on pressure levels. All data are downloaded from the Copernicus Climate Data Store (https://cds.climate.copernicus.eu/) and reorganized for benchmark construction. Please ensure compliance with the CDS Licence when using or redistributing the data.
SeasonBench-EA-DWD-PressureThe dataset is a subset for SeasonBench-EA Benchmark, which contains the ensemble forecasts from DWD on pressure levels.
All data are downloaded from the Copernicus Climate Data Store (https://cds.climate.copernicus.eu/) and reorganized for benchmark construction.
Please ensure compliance with the CDS Licence when using or redistributing the data.
models-under-pressure
Models Under Pressure
This dataset accompanies the paper Detecting High-Stakes Interactions with Activation Probes, presented at the ICML 2025 Workshop on Actionable Interpretability, accepted to NeurIPS 2025.
Overview
Every sample is a user-facing LLM interaction labelled as high-stakes or low-stakes. The label reflects whether the conversation involves potentially consequential outcomes (medical advice, legal matters, financial decisions, etc.) vs. routine queries.
The… See the full description on the dataset page: https://huggingface.co/datasets/Arrrlex/models-under-pressure.SeasonBench-EA-ECCC-PressureThe dataset is a subset for SeasonBench-EA Benchmark, which contains the ensemble forecasts from ECCC on pressure levels. All data are downloaded from the Copernicus Climate Data Store (https://cds.climate.copernicus.eu/) and reorganized for benchmark construction. Please ensure compliance with the CDS Licence when using or redistributing the data.