INDEX

Explanations

instances of the verb "was" and its various forms in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

currently

-0.15

usan

-0.14

ucs

-0.14

 CURRENT

-0.14

Ð¾Ð·Ñĸ

-0.14

ìĸ´ê°Ģ

-0.14

Ð¾Ð³ÐµÐ½

-0.14

otlin

-0.13

krÃ©t

-0.13

:UITableView

-0.13

POSITIVE LOGITS

/is

0.53

nt

0.47

 indeed

0.29

NT

0.28

 able

0.28

 originally

0.26

abi

0.24

nts

0.24

 supposed

0.24

 meant

0.23

Activations Density 0.546%

instances of the verb "was" and its various forms in the text

No Comments

No Known Activations