INDEX

Explanations

terms related to data protection and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ikip

-0.15

ebek

-0.15

ãĥ³ãĥĨãĤ£

-0.14

ensex

-0.14

Ø¯Ø§Ø±ÛĮ

-0.14

ÙĤØ©

-0.13

isel

-0.13

.Timeout

-0.13

umbing

-0.13

coder

-0.13

POSITIVE LOGITS

eza

0.15

Æ°Æ¡ng

0.15

rans

0.15

éĩı

0.14

ë¹

0.14

/control

0.14

åŃĹ

0.14

 Grade

0.14

 Ð£ÐºÑĢÐ°ÑĹÐ½Ð°

0.14

ift

0.14

Activations Density 0.012%

terms related to data protection and regulations

No Comments

No Known Activations