INDEX

Explanations

code snippets, specifically focusing on HTML and JavaScript related to form structures and links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

addy

-0.17

agal

-0.17

ombre

-0.16

pond

-0.14

ackers

-0.14

Gle

-0.14

isclosed

-0.14

 ÑģÐ¼

-0.14

agar

-0.13

thew

-0.13

POSITIVE LOGITS

 Sanford

0.16

/items

0.15

ãĤ·ãĤ¢

0.15

.SelectCommand

0.15

 overridden

0.14

ç«¹

0.14

ican

0.14

nton

0.14

enga

0.14

iyan

0.14

Activations Density 0.226%

code snippets, specifically focusing on HTML and JavaScript related to form structures and links

No Comments

No Known Activations