INDEX

Explanations

terms and phrases related to data collection and sharing practices

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

udd

-0.15

 ÑĢÐµÑĶ

-0.15

Ìī

-0.15

uddle

-0.15

íķ©

-0.15

aza

-0.15

anka

-0.14

iming

-0.14

ÑĥÑĢÑģ

-0.14

idget

-0.13

POSITIVE LOGITS

jaw

0.15

amet

0.14

obra

0.14

0.13

ombres

0.13

 Presentation

0.13

URY

0.13

 Ø§ÙĦØ¨ÙĦØ¯

0.13

sian

0.12

 themselves

0.12

Activations Density 0.196%

terms and phrases related to data collection and sharing practices

No Comments

No Known Activations