INDEX

Explanations

programming-related constructs and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 directly

-0.14

nic

-0.14

bo

-0.14

Nut

-0.14

 Ð°Ð¼

-0.14

sec

-0.13

UIAlertView

-0.13

NA

-0.13

 Straight

-0.13

 rowCount

-0.13

POSITIVE LOGITS

sky

0.17

rocket

0.16

isson

0.16

å¡ļ

0.15

quarters

0.15

ÙħÙĬ

0.15

astr

0.14

ragon

0.14

kÃ©

0.14

èįĴ

0.14

Activations Density 0.000%

programming-related constructs and syntax

No Comments

No Known Activations