INDEX

Explanations

phrases associated with legal processes and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 thereof

-0.15

eyer

-0.15

abr

-0.15

DeviceInfo

-0.14

Affected

-0.14

 Katz

-0.13

 Bieber

-0.13

ë¡ľëĵľ

-0.13

 addCriterion

-0.13

 jadx

-0.13

POSITIVE LOGITS

 Wilkinson

0.15

aret

0.14

 recently

0.14

ington

0.14

.opendaylight

0.14

addock

0.13

ainer

0.13

akh

0.13

 entitled

0.13

misc

0.13

Activations Density 0.522%

phrases associated with legal processes and regulations

No Comments

No Known Activations