INDEX

Explanations

specific entities or key figures associated with various topics, particularly in the context of digital media and professional roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

RTE

-0.14

 Miguel

-0.14

Mig

-0.14

 ë¥

-0.13

ugin

-0.13

IRR

-0.13

Ð¾Ð³Ñĥ

-0.13

 Montreal

-0.13

 Knee

-0.13

<tag

-0.13

POSITIVE LOGITS

 Ther

0.49

 Holmes

0.40

 Therm

0.28

 Elizabeth

0.27

 Silicon

0.27

Hol

0.27

Th

0.26

 ther

0.25

Wal

0.25

Bal

0.24

Activations Density 0.005%

specific entities or key figures associated with various topics, particularly in the context of digital media and professional roles

No Comments

No Known Activations