INDEX

Explanations

references to health-related topics and the promotion of health initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

_TA

-0.16

kea

-0.15

ESH

-0.15

processable

-0.15

Ð¸ÐºÐ¸

-0.15

.AC

-0.14

abet

-0.14

inear

-0.14

clearfix

-0.14

enan

-0.14

POSITIVE LOGITS

CHAN

0.16

andon

0.15

oyer

0.14

rana

0.13

 EITHER

0.13

Ð¾Ð»Ñİ

0.13

 tobacco

0.13

Settings

0.13

 Penal

0.13

 Lynch

0.13

Activations Density 0.063%

references to health-related topics and the promotion of health initiatives

No Comments

No Known Activations