INDEX

Explanations

phrases related to relationships and collaboration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

adge

-0.13

ä¸įå¾Ĺ

-0.13

 Estr

-0.13

 âĢı

-0.13

owi

-0.13

Ø³Ø§Ø¨

-0.13

ÄĽl

-0.13

obo

-0.12

onder

-0.12

auer

-0.12

POSITIVE LOGITS

don

0.44

don

0.37

Don

0.36

Don

0.35

DON

0.32

DON

0.31

_don

0.29

 dont

0.26

 ÑģÑĤÐ°

0.24

"Don

0.22

Activations Density 0.483%

phrases related to relationships and collaboration

No Comments

No Known Activations