INDEX

Explanations

terms related to spatial data analysis and raster graphics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

izi

-0.15

Zwe

-0.14

 Richt

-0.14

ÏĢÎ·

-0.14

.tv

-0.13

izo

-0.13

immel

-0.13

FontSize

-0.13

udio

-0.13

zept

-0.13

POSITIVE LOGITS

 spatial

0.30

 Spatial

0.29

Spatial

0.29

ogr

0.26

ogr

0.25

 shape

0.23

patial

0.23

 layer

0.23

 Shape

0.23

Layer

0.22

Activations Density 0.038%

terms related to spatial data analysis and raster graphics

No Comments

No Known Activations