INDEX

Explanations

information related to social media platform features and updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 tweeting

-0.16

cloak

-0.16

éª¨

-0.16

 tweeted

-0.15

 Flake

-0.14

 Tumblr

-0.14

 retr

-0.14

 selfies

-0.14

QQ

-0.14

online

-0.14

POSITIVE LOGITS

 Stories

0.25

Stories

0.21

 stories

0.20

/story

0.18

 stickers

0.18

 Shops

0.17

ÏĦÏĮ

0.16

 sticker

0.16

stories

0.16

 poll

0.16

Activations Density 0.031%

information related to social media platform features and updates

No Comments

No Known Activations