INDEX

Explanations

numerical values and quantities related to measurements or statistics

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

aug

-0.14

iddi

-0.14

Ø¨ÙĬ

-0.14

ANA

-0.14

ARGS

-0.13

ilities

-0.13

iameter

-0.13

ë¡ľê·¸

-0.13

ãĢĳãĢĲ

-0.13

||

-0.13

POSITIVE LOGITS

 thousand

0.51

 thousands

0.47

0.41

 Thousands

0.37

Thousands

0.34

 Thousand

0.34

 thous

0.33

 à¤¹à¤ľ

0.32

 million

0.29

Activations Density 0.218%

numerical values and quantities related to measurements or statistics

No Comments

No Known Activations