INDEX

Explanations

technical terms related to programming and data structure manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ei

-0.15

annes

-0.15

æ¦

-0.14

@brief

-0.14

Mahon

-0.14

 èĴ

-0.14

 éĸ¢

-0.14

çĶ

-0.14

ssel

-0.14

ä¸ĩåħĥ

-0.14

POSITIVE LOGITS

 topic

0.28

 consumer

0.27

 Topic

0.27

 partition

0.27

 partitions

0.27

 Consumer

0.26

.Topic

0.26

 topics

0.26

Topic

0.25

 Kafka

0.24

Activations Density 0.008%

technical terms related to programming and data structure manipulation

No Comments

No Known Activations