INDEX

Explanations

references to academic publications and their citation details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ockey

-0.17

bef

-0.16

elsing

-0.15

ocities

-0.14

 Convention

-0.14

ì£¼ìĭľ

-0.14

inx

-0.14

bere

-0.13

.Double

-0.13

ferences

-0.13

POSITIVE LOGITS

ACS

0.22

ACS

0.20

 Accounts

0.18

 ÙħØ§ÛĮÙĦ

0.17

Accounts

0.17

Ang

0.16

Org

0.16

acs

0.16

Org

0.16

 KÃ¼rt

0.15

Activations Density 0.022%

references to academic publications and their citation details

No Comments

No Known Activations