INDEX

Explanations

questions or inquiries about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

mente

-0.15

icios

-0.14

erate

-0.14

hill

-0.13

 Britann

-0.13

halt

-0.13

mlin

-0.13

gin

-0.13

hana

-0.13

ston

-0.13

POSITIVE LOGITS

 else

0.19

soever

0.18

-Ð½Ð¸Ð±ÑĥÐ´ÑĮ

0.17

ToDo

0.16

Ð¾ÑĩÐ½Ð¾

0.16

æł·çļĦ

0.16

 happened

0.15

Î½Î¿Ïį

0.15

-ÑĤÐ¾

0.15

frm

0.14

Activations Density 0.167%

questions or inquiries about various subjects

No Comments

No Known Activations