INDEX

Explanations

references to social media functionalities 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Zoom

-0.16

 Zoom

-0.15

yleft

-0.15

Ø§Ø²ÛĮ

-0.15

å½ķ

-0.14

-Cs

-0.14

 texting

-0.14

 skype

-0.14

 callers

-0.14

 UITextView

-0.13

POSITIVE LOGITS

 feed

0.43

 feeds

0.38

 Feed

0.37

feed

0.35

-feed

0.35

_feed

0.34

Feed

0.32

 news

0.32

.feed

0.30

/feed

0.30

Activations Density 0.085%

references to social media functionalities and updates

No Comments

No Known Activations