INDEX

Explanations

references to social media engagement and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

indow

-0.16

occo

-0.15

è§

-0.15

olson

-0.14

 Affero

-0.14

irs

-0.14

otto

-0.14

dna

-0.14

ë²Ħ

-0.14

aris

-0.14

POSITIVE LOGITS

 Instagram

0.32

Instagram

0.29

 social

0.28

 instagram

0.26

 Twitter

0.25

 twitter

0.24

 INST

0.23

Twitter

0.23

 Facebook

0.23

social

0.22

Activations Density 0.053%

references to social media engagement and interactions

No Comments

No Known Activations