INDEX

Explanations

geographic locations and proper nouns related to counties and regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

zik

-0.15

istrovstvÃŃ

-0.15

 Erotik

-0.15

ycl

-0.14

ich

-0.14

 fused

-0.13

ongyang

-0.13

processable

-0.13

caÃ§Ã£o

-0.13

POSITIVE LOGITS

urtle

0.16

åĮħ

0.15

olvers

0.15

enders

0.14

ity

0.14

endas

0.14

ovna

0.14

éļ¨

0.14

ãĤ¦ãĤ§

0.14

ãĥĭãĤ¢

0.13

Activations Density 0.111%

geographic locations and proper nouns related to counties and regions

No Comments

No Known Activations