INDEX

Explanations

terms related to legal actions and prosecution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ook

-0.15

rosse

-0.15

gel

-0.14

Asi

-0.14

emann

-0.14

 moot

-0.14

.inline

-0.14

Ø¬Ø¯

-0.14

POSITIVE LOGITS

DMI

0.17

amen

0.15

/respond

0.15

Ð¸ÑĢÐ°

0.15

siblings

0.15

 ancest

0.15

 ëĭ¤ìļ´ë°Ľê¸°

0.14

ussen

0.14

ESCO

0.14

ÑĮÐºÐ¾

0.14

Activations Density 0.005%

terms related to legal actions and prosecution

No Comments

No Known Activations