INDEX

Explanations

items related to formatting and structuring content in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

dej

-0.16

itore

-0.15

à¸Ħà¸Ńà¸¡

-0.15

è°±

-0.15

REFERRED

-0.14

aisal

-0.14

áºŃu

-0.14

kenin

-0.14

)((((

-0.14

oulder

-0.14

POSITIVE LOGITS

 Burton

0.16

-reset

0.15

 Alle

0.14

allon

0.14

 Addison

0.14

 Stephanie

0.13

 localtime

0.13

 stdClass

0.13

 Allan

0.13

Activations Density 0.011%

items related to formatting and structuring content in documents

No Comments

No Known Activations