INDEX

Explanations

references to popular television shows and their cultural implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ervo

-0.16

ivi

-0.16

ÐµÐ´Ð°Ðº

-0.15

.codec

-0.14

vod

-0.14

erli

-0.14

.Transactional

-0.14

afort

-0.13

lemn

-0.13

agrant

-0.13

POSITIVE LOGITS

 sitcom

0.32

 Rose

0.28

Sit

0.24

Rose

0.23

ABC

0.22

 comedy

0.22

sit

0.22

Sit

0.21

 Comedy

0.20

ABC

0.20

Activations Density 0.064%

references to popular television shows and their cultural implications

No Comments

No Known Activations