INDEX

Explanations

terms related to online streaming and media content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

velte

-0.16

pre

-0.15

utsch

-0.15

chan

-0.14

ST

-0.14

imid

-0.14

ium

-0.14

ush

-0.14

-of

-0.14

POSITIVE LOGITS

iterals

0.17

ertest

0.15

Ø±ÙĪÛĮ

0.15

xlim

0.14

viÄį

0.14

zug

0.14

ÙĬØªÙĬ

0.13

_ATTRIB

0.13

 lÃ¡

0.13

owa

0.13

Activations Density 0.008%

terms related to online streaming and media content

No Comments

No Known Activations