INDEX

Explanations

references to the availability and features of streaming content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 telev

-0.17

è°±

-0.16

alus

-0.15

ãĥĥãĤ°

-0.15

atron

-0.15

 televis

-0.14

à¸Ļà¸²à¸¡

-0.14

.zh

-0.14

à¤Łà¤ķ

-0.14

erap

-0.14

POSITIVE LOGITS

 shows

0.28

 content

0.27

 programming

0.24

 Shows

0.24

 titles

0.23

shows

0.22

 library

0.22

 programs

0.21

 exclusive

0.21

 exclus

0.20

Activations Density 0.059%

references to the availability and features of streaming content

No Comments

No Known Activations