INDEX

Explanations

references to citations and authors in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Ä°nsan

-0.20

 DÃ¼ny

-0.17

Ãį

-0.17

 BÃ¶lÃ¼m

-0.16

 BazÄ±

-0.16

 MÃ¼ÅŁ

-0.16

 áº

-0.16

 Onun

-0.15

 Ãĸzellikle

-0.15

 Ä°st

-0.15

POSITIVE LOGITS

Oz

0.24

Erd

0.23

Ì§

0.22

Dog

0.22

 Kurt

0.21

Alt

0.21

Nec

0.20

Ser

0.20

erdem

0.20

orman

0.20

Activations Density 0.028%

references to citations and authors in academic contexts

No Comments

No Known Activations