INDEX

Explanations

structured data fields and identifiers typically associated with database schemas

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

rys

-0.15

ylene

-0.15

rix

-0.14

ysi

-0.14

 Chain

-0.13

omo

-0.13

.timestamp

-0.13

raya

-0.13

 joint

-0.13

 benef

-0.13

POSITIVE LOGITS

ÐµÐ¿ÑĤÐ¸

0.17

awl

0.15

stad

0.15

insky

0.15

modelName

0.14

strup

0.14

Ã¤nn

0.14

£

0.14

umont

0.14

izzo

0.14

Activations Density 0.080%

structured data fields and identifiers typically associated with database schemas

No Comments

No Known Activations