INDEX

Explanations

legal terminology and concepts related to court decisions and remedies

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

 unus

-0.15

 predis

-0.15

æŀ

-0.15

 ineligible

-0.14

 subj

-0.14

 unfavorable

-0.14

 embargo

-0.13

anki

-0.13

obi

-0.13

Ã¤ge

-0.13

POSITIVE LOGITS

 appropriate

0.30

appropriate

0.29

 proper

0.28

 justified

0.25

 fair

0.25

 sound

0.23

sound

0.23

ropriate

0.23

 proportion

0.21

 proport

0.21

Activations Density 0.212%

legal terminology and concepts related to court decisions and remedies

No Comments

No Known Activations