INDEX

Explanations

references to significant dates and publication years

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

ÑģÐµ

-0.17

 tane

-0.16

utin

-0.15

etin

-0.14

Ø§ÙĨØª

-0.13

ÄĽn

-0.13

illis

-0.13

emap

-0.13

 hÃ¢l

-0.13

 celkem

-0.13

POSITIVE LOGITS

 recent

0.41

 recently

0.38

recent

0.38

 Recently

0.30

Recently

0.30

 last

0.28

Recent

0.27

 Recent

0.27

æľĢè¿ĳ

0.25

_recent

0.25

Activations Density 0.103%

references to significant dates and publication years

No Comments

No Known Activations