INDEX

Explanations

legal terminology and references related to court proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

QUENCE

-0.17

ÐµÑİ

-0.16

Fetcher

-0.16

èĮĥ

-0.15

izace

-0.15

anne

-0.14

rÃ¡n

-0.14

Äįer

-0.14

lags

-0.13

 appellate

-0.13

POSITIVE LOGITS

 motion

0.38

 motions

0.37

 Motion

0.36

Motion

0.32

motion

0.31

 summary

0.29

-motion

0.28

.motion

0.28

_motion

0.27

summary

0.26

Activations Density 0.103%

legal terminology and references related to court proceedings

No Comments

No Known Activations