INDEX

Explanations

references to lists and compiling information

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

hole

-0.15

/language

-0.15

bourg

-0.14

ä¼ı

-0.14

ulo

-0.14

 Lump

-0.14

oland

-0.14

unker

-0.13

LOB

-0.13

lernen

-0.13

POSITIVE LOGITS

 list

0.69

list

0.46

 List

0.46

 lists

0.46

.list

0.42

-list

0.40

_list

0.40

	list

0.39

 ÑģÐ¿Ð¸ÑģÐ¾Ðº

0.38

 lista

0.38

Activations Density 0.169%

references to lists and compiling information

No Comments

No Known Activations