INDEX

Explanations

copyright-related phrases and indications

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

anders

-0.16

 Siege

-0.16

tr

-0.16

Tr

-0.15

Mal

-0.15

 Malk

-0.14

 ÐľÐ°Ð»

-0.14

POSITIVE LOGITS

ulings

0.16

isphere

0.16

Ã£ng

0.15

/Dk

0.15

ÑģÑĤÑĢÑĥ

0.15

Ð¶Ð½Ð¾

0.15

urons

0.15

Ø§ÙĨØ³

0.14

 Orders

0.14

furt

0.14

Activations Density 0.008%

copyright-related phrases and indications

No Comments

No Known Activations