INDEX

Explanations

key phrases and elements related to popularity and potential impact in various contexts

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

.are

-0.18

 stuff

-0.15

imli

-0.15

åĲĦç§į

-0.15

ä¸ĢæŃ¥

-0.14

ØºØ§ÙĦ

-0.14

Ð½Ð¾ÑģÑıÑĤ

-0.14

Ð¾Ð²Ð¸Ñĩ

-0.14

SSID

-0.14

 everywhere

-0.13

POSITIVE LOGITS

few

0.18

bara

0.18

arda

0.17

esti

0.17

ascar

0.16

Few

0.15

 Chew

0.15

ä¹ĭä¸Ģ

0.15

 pieces

0.14

vou

0.14

Activations Density 0.263%

key phrases and elements related to popularity and potential impact in various contexts

No Comments

No Known Activations