INDEX

Explanations

references to information technology and its related terms

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

hausen

-0.18

hid

-0.16

hist

-0.16

gency

-0.15

iciel

-0.15

holes

-0.15

PRINTF

-0.15

Ð½ÑĤ

-0.15

ipers

-0.15

stell

-0.14

POSITIVE LOGITS

unes

0.29

ä¿

0.21

inerary

0.20

(IT

0.20

 infra

0.19

infra

0.18

.IsAny

0.18

IL

0.17

 support

0.17

 infrastructure

0.17

Activations Density 0.015%

references to information technology and its related terms

No Comments

No Known Activations