INDEX

Explanations

phrases and terms related to legal and formal documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 cent

-0.15

elig

-0.15

-cent

-0.14

olo

-0.14

 scaff

-0.14

 eskort

-0.14

enge

-0.14

iese

-0.14

Sv

-0.14

umer

-0.14

POSITIVE LOGITS

prung

0.17

dÃ¡l

0.16

 ZÃ¡kladnÃŃ

0.15

uger

0.15

jury

0.15

ausible

0.15

ENTE

0.14

*>*

0.14

ÄĽr

0.14

å§¿

0.14

Activations Density 0.037%

phrases and terms related to legal and formal documentation

No Comments

No Known Activations