INDEX

Explanations

references to technical specifications or features of products and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

annah

-0.14

ago

-0.14

amt

-0.14

 compliments

-0.14

alone

-0.14

aul

-0.14

 compliment

-0.13

 undertaking

-0.13

strup

-0.13

Å¡it

-0.13

POSITIVE LOGITS

 contain

0.42

 contains

0.39

contain

0.34

 Contains

0.31

contains

0.30

 containing

0.28

Contain

0.28

Contains

0.28

 ÑģÐ¾Ð´ÐµÑĢÐ¶

0.25

 Ø¯Ø§Ø±Ø§ÛĮ

0.24

Activations Density 0.464%

references to technical specifications or features of products and systems

No Comments

No Known Activations