INDEX

Explanations

terms related to quality, production, and specific industries like food science or garment manufacturing

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

ipur

-0.16

ist

-0.15

sen

-0.15

ipp

-0.14

ennis

-0.14

Rek

-0.14

ugh

-0.14

resh

-0.14

ÙħØ§Ø±ÛĮ

-0.14

lop

-0.14

POSITIVE LOGITS

adlo

0.16

iling

0.15

 AydÄ±n

0.15

0.14

[email

0.14

ØµÙĪØ±

0.14

ï»¿#

0.14

uling

0.13

/releases

0.13

vnÃŃ

0.13

Activations Density 0.002%

terms related to quality, production, and specific industries like food science or garment manufacturing

No Comments

No Known Activations