INDEX

Explanations

technical references to programming structures and properties

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

 counterparts

-0.15

OperationException

-0.15

abus

-0.15

inger

-0.14

INGER

-0.14

isEnabled

-0.14

 similarly

-0.14

 nomine

-0.13

reste

-0.13

POSITIVE LOGITS

 equal

0.45

equal

0.33

 equals

0.32

 Equal

0.32

 ÑĢÐ°Ð²

0.29

Equal

0.28

 igual

0.27

 Ø¨Ø±Ø§Ø¨Ø±

0.26

 EQUAL

0.26

.equal

0.25

Activations Density 0.201%

technical references to programming structures and properties

No Comments

No Known Activations