INDEX

Explanations

technical terms related to boot processes and hardware

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

bel

-0.17

Din

-0.16

 Bast

-0.16

 Budd

-0.15

-0.14

 recip

-0.14

_OBJC

-0.14

dov

-0.14

Sen

-0.13

POSITIVE LOGITS

 boot

0.41

 Boot

0.38

boot

0.38

/boot

0.36

 BOOT

0.35

Boot

0.35

-boot

0.34

 boots

0.34

_boot

0.33

 Boots

0.32

Activations Density 0.049%

technical terms related to boot processes and hardware

No Comments

No Known Activations