INDEX

Explanations

legal terminology and references to jurisdiction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

iesel

-0.15

æĴ

-0.15

 Prosec

-0.15

escal

-0.15

ittel

-0.15

asel

-0.14

chu

-0.14

ITTE

-0.14

 VerfÃ¼gung

-0.14

egl

-0.13

POSITIVE LOGITS

 jurisdiction

0.32

 forum

0.27

forum

0.23

Jur

0.23

isdiction

0.21

Jur

0.21

 extr

0.21

 Extr

0.21

 Forum

0.20

jur

0.20

Activations Density 0.038%

legal terminology and references to jurisdiction

No Comments

No Known Activations