INDEX

Explanations

references to notable events or historical narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.39

 xrange

-0.35

 Zika

-0.34

 âĢª

-0.33

 Ebola

-0.32

Û²Û°Û±

-0.31

 Huffington

-0.30

 Obama

-0.29

 tslint

-0.28

 Skype

-0.27

POSITIVE LOGITS

0.56

Tik

0.45

 Biden

0.44

 covid

0.41

 Covid

0.41

 COVID

0.40

Û²Û°Û²

0.40

 pandemic

0.33

ðĿ

0.33

tik

0.32

Activations Density 1.193%

references to notable events or historical narratives

No Comments

No Known Activations