INDEX

Explanations

references to international topics or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

åħ¨åĽ½

-0.17

iller

-0.16

ÑģÑı

-0.15

orian

-0.15

Ú¯Ø§Ùĩ

-0.15

za

-0.15

soever

-0.15

 Nationwide

-0.15

ãĤ¥

-0.14

POSITIVE LOGITS

ized

0.32

ization

0.31

isation

0.28

ize

0.27

izing

0.26

/dom

0.26

ised

0.26

ise

0.24

izes

0.24

-standard

0.24

Activations Density 0.025%

references to international topics or organizations

No Comments

No Known Activations