INDEX

Explanations

phrases that indicate relationships or connections between entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

osit

-0.16

ä¹Ī

-0.16

elan

-0.15

 cáº£

-0.15

ickle

-0.15

 Ð´ÑĢÑĥÐ³Ð¾Ð³Ð¾

-0.15

Ø¹Ø¨

-0.15

another

-0.14

 Ð´ÑĢÑĥÐ³Ð¾Ð¹

-0.14

ãĥ¼ãĤº

-0.14

POSITIVE LOGITS

/am

0.31

two

0.23

 sexes

0.23

 them

0.21

 ÑģÐ¾Ð±Ð¾Ð¹

0.21

âĢĮØ§ÙĦÙħÙĦÙĦÛĮ

0.20

 ÑģÐ¾Ð±Ð¾Ñİ

0.18

 genders

0.18

 these

0.18

/about

0.18

Activations Density 0.066%

phrases that indicate relationships or connections between entities

No Comments

No Known Activations