INDEX

Explanations

programming-related terms or components

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

ÑĢÐµÑģ

-0.15

aticon

-0.15

Ã¼ml

-0.14

Ã£n

-0.14

adla

-0.14

ansom

-0.14

amburger

-0.14

 Ulus

-0.13

]>=

-0.13

-eslint

-0.13

POSITIVE LOGITS

 form

0.25

 Submission

0.21

 submission

0.20

FormData

0.20

 submit

0.20

 submitting

0.20

csrf

0.20

submit

0.20

 Form

0.19

-submit

0.19

Activations Density 0.235%

programming-related terms or components

No Comments

No Known Activations