INDEX

Explanations

specific terminology related to educational or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

isay

-0.15

thers

-0.13

Ø¨Ø§ÙĨ

-0.13

amel

-0.13

UCCEEDED

-0.13

ç¨¿

-0.13

 while

-0.12

odem

-0.12

 trib

-0.12

.zone

-0.12

POSITIVE LOGITS

 because

0.55

because

0.51

 porque

0.45

ï¼ĮåĽłä¸º

0.43

Because

0.43

 Because

0.42

åĽłä¸º

0.40

 perchÃ©

0.38

 karena

0.37

ecause

0.37

Activations Density 0.002%

specific terminology related to educational or programming contexts

No Comments

No Known Activations