INDEX

Explanations

occurrences of the word "post" and its variations in the context of sharing content or updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 postfix

-0.24

Post

-0.21

 POST

-0.20

 postal

-0.20

 Post

-0.20

PostBack

-0.20

 Posts

-0.20

POST

-0.20

Posts

-0.19

_posts

-0.19

POSITIVE LOGITS

ulate

0.35

mort

0.32

hum

0.31

-mort

0.28

script

0.27

ulated

0.27

greSQL

0.27

card

0.26

ulates

0.26

graduate

0.26

Activations Density 0.058%

occurrences of the word "post" and its variations in the context of sharing content or updates

No Comments

No Known Activations