INDEX

Explanations

product specifications and details related to technology items

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

ambre

-0.17

alars

-0.15

.osgi

-0.14

wagon

-0.14

apas

-0.14

taj

-0.14

 boilers

-0.13

probe

-0.13

 loadChildren

-0.13

ë¥

-0.13

POSITIVE LOGITS

 case

0.34

 cases

0.32

 Case

0.31

 Cases

0.30

Case

0.29

Cases

0.26

 CASE

0.26

cases

0.26

case

0.26

 protector

0.25

Activations Density 0.018%

product specifications and details related to technology items

No Comments

No Known Activations