INDEX

Explanations

terms and concepts related to diversity and inclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

arena

-0.15

inner

-0.15

ç°

-0.14

 arena

-0.14

æĿī

-0.14

 Venue

-0.14

ÑĤÑĢÐ¸

-0.14

lier

-0.14

legation

-0.14

Ze

-0.14

POSITIVE LOGITS

ElementException

0.15

Tau

0.15

Orr

0.14

 Laden

0.14

andalone

0.13

 Correct

0.13

Ð¾Ð¿Ð¸Ñģ

0.13

gend

0.13

 interrupt

0.13

ows

0.13

Activations Density 0.136%

terms and concepts related to diversity and inclusion

No Comments

No Known Activations