INDEX

Explanations

event names and their associated details from technology and automotive shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 fitting

-0.15

Dal

-0.15

ãĥĭãĤ¢

-0.14

Ð¸Ð½Ð¾Ð¹

-0.14

azi

-0.14

Ã¼nchen

-0.14

ãĥĳãĥ³

-0.14

PG

-0.14

agra

-0.14

 purs

-0.14

POSITIVE LOGITS

 LENG

0.16

ÙĥÙĩ

0.15

Slinky

0.15

ÙĨÛĮÙĨ

0.14

 EXEMPLARY

0.14

ãĥ¼ãĥĭ

0.13

kop

0.13

Äįan

0.13

 jspb

0.13

ÙħØª

0.13

Activations Density 0.019%

event names and their associated details from technology and automotive shows

No Comments

No Known Activations