INDEX

Explanations

references to social media moderation and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

leck

-0.16

ÑĤÑĢÐ¾Ð½

-0.15

 Tablet

-0.15

reff

-0.15

tablet

-0.15

 tablet

-0.15

 Lair

-0.14

RSS

-0.14

|max

-0.14

sector

-0.14

POSITIVE LOGITS

 moderation

0.31

 Moder

0.26

 removal

0.26

 moder

0.25

 moderators

0.25

 Removal

0.23

Moder

0.23

 removed

0.22

 removing

0.22

 flags

0.22

Activations Density 0.037%

references to social media moderation and its implications

No Comments

No Known Activations