INDEX

Explanations

information related to data visualization techniques and charts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-regexp

-0.15

ãĤĨ

-0.15

/photos

-0.15

Vault

-0.14

rons

-0.14

.plist

-0.14

á»ĵn

-0.14

/gcc

-0.13

ãĥŃãĥ³

-0.13

ifestyles

-0.13

POSITIVE LOGITS

 chart

0.52

 charts

0.45

 Chart

0.42

 graph

0.40

chart

0.39

Chart

0.38

-chart

0.37

 plot

0.36

bar

0.36

 graphs

0.35

Activations Density 0.265%

information related to data visualization techniques and charts

No Comments

No Known Activations