INDEX

Explanations

references to exhibition dates and time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ello

-0.19

ãĥĥ

-0.15

 Begins

-0.14

ManagerInterface

-0.14

nard

-0.14

illo

-0.14

Begin

-0.14

ilo

-0.14

kid

-0.14

NEY

-0.14

POSITIVE LOGITS

yne

0.19

noinspection

0.17

@end

0.16

 close

0.16

 next

0.16

 basic

0.16

end

0.16

igate

0.15

_IMPLEMENT

0.15

WL

0.15

Activations Density 0.059%

references to exhibition dates and time periods

No Comments

No Known Activations