INDEX

Explanations

specific terminology and phrases related to legal contexts and 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ã¨o

-0.15

ankind

-0.13

 Castro

-0.13

tr

-0.13

 Lambert

-0.13

 Stark

-0.12

ÑĥÐ»Ñı

-0.12

de

-0.12

 Specialists

-0.12

POSITIVE LOGITS

¶ģ

0.17

'gc

0.16

.scalablytyped

0.16

«ĺ

0.16

 TMPro

0.15

¦¬

0.14

Ð³Ð°Ð»Ñĸ

0.13

 backpage

0.13

¯¼

0.13

ï¼Ĭ

0.13

Activations Density 17.567%

specific terminology and phrases related to legal contexts and court proceedings

No Comments

No Known Activations