INDEX

Explanations

references to specific elements or characters in the Star Wars franchise

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

croft

-0.16

atte

-0.15

 Dion

-0.14

æ´¥

-0.14

ce

-0.14

als

-0.13

Fut

-0.13

 Victorian

-0.13

Ð´Ð¾Ð²

-0.13

ÏįÏĢ

-0.13

POSITIVE LOGITS

Lens

0.16

ahoo

0.16

endor

0.16

ÅĻiv

0.14

ropa

0.14

ustain

0.14

ertools

0.14

ãģ©ãģĨ

0.14

 ÐĴÐ¸Ð´

0.14

 ÑĢÐ°Ð

0.14

Activations Density 0.050%

references to specific elements or characters in the Star Wars franchise

No Comments

No Known Activations