INDEX

Explanations

phrases related to legal and regulatory processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

zar

-0.16

 schwar

-0.15

erte

-0.15

ÏģÎ±Î²

-0.14

idis

-0.14

jev

-0.14

Ð¾Ð´Ð°ÑĢ

-0.14

ovsky

-0.14

gow

-0.14

erp

-0.14

POSITIVE LOGITS

 Samoa

0.26

 Fiji

0.20

 Papua

0.19

iT

0.18

 mata

0.17

 Solomon

0.17

 tertiary

0.17

 Guam

0.17

 Cabinet

0.16

 respective

0.16

Activations Density 0.006%

phrases related to legal and regulatory processes

No Comments

No Known Activations