INDEX

Explanations

dates and numerical information relevant to events or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 COVID

-0.53

 Covid

-0.50

 covid

-0.50

COVID

-0.46

 pandemic

-0.41

 Coronavirus

-0.38

Tik

-0.38

 coronavirus

-0.37

 Biden

-0.34

 Zoom

-0.34

POSITIVE LOGITS

0.85

Û²Û°Û±

0.57

 tumblr

0.27

umblr

0.26

 Tumblr

0.26

 Obamacare

0.26

 Huffington

0.24

 âĢª

0.24

 Hollande

0.24

 Zika

0.23

Activations Density 0.235%

dates and numerical information relevant to events or reports

No Comments

No Known Activations