INDEX

Explanations

numerical values or identifiers, particularly related to addresses or codes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

odi

-0.16

antan

-0.15

erk

-0.15

erp

-0.15

pars

-0.14

 Giang

-0.14

yt

-0.13

ëĿ¼ëıĦ

-0.13

iant

-0.13

Bye

-0.13

POSITIVE LOGITS

adnÃŃ

0.16

imals

0.15

à§į

0.15

/MIT

0.15

.inflate

0.14

zers

0.14

abilia

0.14

adia

0.14

 sayÄ±lÄ±

0.14

 OMIT

0.13

Activations Density 0.040%

numerical values or identifiers, particularly related to addresses or codes

No Comments

No Known Activations