INDEX

Explanations

elements related to legal terminology and procedures

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

acad

-0.15

.Interop

-0.14

icros

-0.14

Å¥

-0.13

elig

-0.13

rypto

-0.13

abox

-0.13

æĺĩ

-0.13

icast

-0.13

 spons

-0.12

POSITIVE LOGITS

ret

0.38

 hourly

0.35

 retain

0.33

 billed

0.28

 Hour

0.28

Ret

0.27

 billing

0.27

 bill

0.25

Ret

0.24

hour

0.24

Activations Density 0.078%

elements related to legal terminology and procedures

No Comments

No Known Activations