INDEX

Explanations

occurrences of the word "letter" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

yas

-0.17

emaker

-0.17

ARDS

-0.15

sale

-0.15

yum

-0.15

Ð»ÑıÐ½

-0.15

slu

-0.15

zdy

-0.15

yan

-0.15

yor

-0.14

POSITIVE LOGITS

press

0.31

head

0.28

atura

0.22

ing

0.21

 addressed

0.21

ed

0.20

/email

0.20

-writing

0.19

 sent

0.19

headed

0.19

Activations Density 0.025%

occurrences of the word "letter" and related terms

No Comments

No Known Activations

occurrences of the word "letter" and related terms

No Comments

No Known Activations