INDEX

Explanations

references to competition rankings and positions in races

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

Å¡ÃŃ

-0.15

bell

-0.15

rais

-0.15

iais

-0.14

 ally

-0.14

erli

-0.14

bridge

-0.14

 bridge

-0.13

éº

-0.13

 sight

-0.13

POSITIVE LOGITS

	Copyright

0.15

heritance

0.14

 limburg

0.14

ationToken

0.14

BuilderFactory

0.14

iÅ¾

0.14

 COMMENTS

0.14

gan

0.14

wahl

0.13

ctp

0.13

Activations Density 0.019%

references to competition rankings and positions in races

No Comments

No Known Activations