INDEX

Explanations

terms related to violations of rules and regulations, especially regarding substance use and integrity in sports

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

ehler

-0.18

inki

-0.14

UAL

-0.14

 immobil

-0.13

iddles

-0.13

_patterns

-0.13

 siÃ¨

-0.13

sov

-0.13

quez

-0.13

 Engl

-0.13

POSITIVE LOGITS

_hdl

0.16

ÐĶÐļ

0.15

Å¥

0.15

adol

0.14

ysa

0.14

Downloader

0.14

ÑģÑĮÐº

0.14

ochond

0.14

ulace

0.13

Ð½Ð°Ðº

0.13

Activations Density 0.020%

terms related to violations of rules and regulations, especially regarding substance use and integrity in sports

No Comments

No Known Activations