INDEX

Explanations

terms and references related to the fitness industry and mental health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

cia

-0.15

reamble

-0.15

andon

-0.14

finity

-0.14

rias

-0.14

arrass

-0.14

oub

-0.14

urch

-0.14

ãĥĢãĥ¼

-0.13

ached

-0.13

POSITIVE LOGITS

 simply

0.25

 simplement

0.20

sometimes

0.19

 sometimes

0.19

 Ð¿ÑĢÐ¾ÑģÑĤÐ¾

0.19

 occasionally

0.17

ients

0.17

 ÙĩÙħØ§ÙĨ

0.17

 Simply

0.16

 Ð°Ð½Ð³Ð»

0.16

Activations Density 0.222%

terms and references related to the fitness industry and mental health

No Comments

No Known Activations