INDEX

Explanations

legal terms and references related to plaintiffs, defendants, and appeals in a court context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

fect

-0.15

egin

-0.15

MESS

-0.15

illi

-0.15

à¤²à¤¤

-0.14

endoza

-0.14

antt

-0.14

Ø±Ø¯

-0.14

tog

-0.14

 èĭ

-0.14

POSITIVE LOGITS

0.15

nuts

0.15

iele

0.15

ãĥ¼ãĤº

0.14

 Gaul

0.14

rych

0.14

berger

0.14

aniu

0.14

lein

0.14

Activations Density 0.057%

legal terms and references related to plaintiffs, defendants, and appeals in a court context

No Comments

No Known Activations