INDEX

Explanations

references to significant events or changes in status

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

 after

-0.28

 soon

-0.24

after

-0.22

_after

-0.20

 sooner

-0.19

 Ð¿Ð¾ÑģÐ»Ðµ

-0.19

 aprÃ¨s

-0.19

 dopo

-0.19

 AFTER

-0.19

 despuÃ©s

-0.18

POSITIVE LOGITS

 ÙħØ¨Ø§Ø´

0.31

 expires

0.22

 subs

0.19

 occurs

0.18

subs

0.18

 began

0.17

 ends

0.17

 occurred

0.17

 date

0.16

//{{

0.16

Activations Density 0.165%

references to significant events or changes in status

No Comments

No Known Activations