INDEX

Explanations

references to legal verdicts and judgments

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

ÑĩÑĥÐº

-0.14

ÑĮÐºÐ¾

-0.14

å£

-0.13

labs

-0.13

/GPL

-0.13

å¿Ļ

-0.13

adden

-0.13

 Arrest

-0.13

Charge

-0.13

illance

-0.13

POSITIVE LOGITS

 damages

0.46

 compens

0.41

 awards

0.40

 compensation

0.39

 award

0.39

 awarded

0.36

dam

0.35

 damage

0.34

 compensate

0.34

 Award

0.33

Activations Density 0.283%

references to legal verdicts and judgments

No Comments

No Known Activations