INDEX

Explanations

information related to fees and inclusivity of services or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Buckley

-0.15

iske

-0.15

 Harding

-0.15

ternal

-0.15

lingen

-0.15

aket

-0.14

okes

-0.14

 GarcÃŃa

-0.14

ackets

-0.14

POSITIVE LOGITS

 gratis

0.40

 FREE

0.32

 free

0.32

 Gratis

0.30

free

0.30

åħįè´¹

0.29

gratis

0.29

FREE

0.29

Gratis

0.29

à¸Łà¸£

0.28

Activations Density 0.239%

information related to fees and inclusivity of services or activities

No Comments

No Known Activations