INDEX

Explanations

references to awards and recognitions in a community or professional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ieg

-0.18

ubat

-0.17

 pitch

-0.15

 REFER

-0.15

èĪĪ

-0.14

mour

-0.14

åħ´

-0.14

Ã¡o

-0.14

ader

-0.14

pitch

-0.14

POSITIVE LOGITS

 selection

0.23

 awards

0.22

 award

0.22

 recipients

0.22

 ìĪĺìĥģ

0.22

aw

0.21

 criteria

0.20

 nominations

0.20

 selections

0.20

 nominees

0.20

Activations Density 0.090%

references to awards and recognitions in a community or professional context

No Comments

No Known Activations