INDEX

Explanations

numerical values and specific references to locations or photography events

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

enie

-0.15

ale

-0.15

-0.14

ensa

-0.14

agn

-0.14

 ä½Ĳ

-0.13

eld

-0.13

enance

-0.13

ayload

-0.13

POSITIVE LOGITS

ourg

0.15

Elf

0.15

Ø§Ø²ÛĮ

0.14

deaux

0.14

Ã¡c

0.13

 defaultManager

0.13

Wunused

0.13

ë°Ģ

0.13

Disposed

0.13

(WIN

0.13

Activations Density 0.012%

numerical values and specific references to locations or photography events

No Comments

No Known Activations