INDEX

Explanations

discussions surrounding internet policies and regulations

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

arias

-0.16

CRM

-0.15

phetamine

-0.14

ardu

-0.14

 discharged

-0.14

_PROC

-0.14

 eÅŁ

-0.13

 hang

-0.13

avra

-0.13

POSITIVE LOGITS

 blocking

0.31

 blocks

0.31

 blocked

0.30

 block

0.30

 filtering

0.29

 Filtering

0.27

 Blocks

0.27

 content

0.27

blocking

0.27

 Blocked

0.26

Activations Density 0.025%

discussions surrounding internet policies and regulations

No Comments

No Known Activations