INDEX

Explanations

instances of the word "that" and its variations in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 accordingly

-0.14

\grid

-0.13

ocs

-0.13

&R

-0.13

duÄŁunu

-0.12

/***/

-0.12

 lett

-0.12

_:*

-0.12

-inf

-0.12

minster

-0.12

POSITIVE LOGITS

 plus

0.72

plus

0.56

ä»¥åıĬ

0.55

 PLUS

0.54

ï¼Įä»¥åıĬ

0.52

 samt

0.47

 Plus

0.46

Plus

0.45

 sowie

0.45

 along

0.43

Activations Density 0.001%

instances of the word "that" and its variations in sentences

No Comments

No Known Activations