INDEX

Explanations

significant punctuations and transitions in writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

à¥Ģà¤Ľ

-0.16

åıªæĺ¯

-0.15

eras

-0.14

à¸Ĭà¸Ńà¸ļ

-0.13

zimmer

-0.13

åĲİçļĦ

-0.13

emann

-0.13

 tÃŃch

-0.13

Its

-0.12

zac

-0.12

POSITIVE LOGITS

 Enter

0.43

Enter

0.42

 enter

0.40

 Fortunately

0.34

enter

0.34

.Enter

0.32

.enter

0.32

 Luckily

0.32

 therefore

0.32

Fortunately

0.31

Activations Density 0.309%

significant punctuations and transitions in writing

No Comments

No Known Activations