INDEX

Explanations

rankings or positions related to events or competitions

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

ÐµÑĢÐ°Ð»ÑĮ

-0.15

illac

-0.15

 hrÃ¡

-0.14

ucc

-0.14

igo

-0.14

ilogy

-0.14

ç´Ļ

-0.14

éļĨ

-0.13

 Marathon

-0.13

.Player

-0.13

POSITIVE LOGITS

 gymn

0.35

Gym

0.29

 beam

0.27

 vault

0.26

 Vault

0.26

 floor

0.25

Floor

0.25

tum

0.25

 Floor

0.25

Vault

0.24

Activations Density 0.022%

rankings or positions related to events or competitions

No Comments

No Known Activations