INDEX

Explanations

legal terminology and references to lawsuits or legal actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

getDrawable

-0.15

_annotations

-0.14

rint

-0.14

 Cabinet

-0.13

lund

-0.13

.Interop

-0.13

lena

-0.13

ogan

-0.13

POSITIVE LOGITS

 class

0.42

 Class

0.32

 certification

0.32

 subclasses

0.31

class

0.29

 classes

0.29

opt

0.29

 subclass

0.29

 Certification

0.28

 certified

0.27

Activations Density 0.052%

legal terminology and references to lawsuits or legal actions

No Comments

No Known Activations