INDEX

Explanations

terms related to exemptions and exceptions in regulations or laws

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

engl

-0.17

Glo

-0.15

inis

-0.15

atori

-0.14

/video

-0.14

COD

-0.14

/memory

-0.14

anki

-0.14

Ã¡g

-0.14

Ð»ÑĥÐ±

-0.14

POSITIVE LOGITS

æİī

0.17

omination

0.17

olini

0.16

0.15

ansson

0.15

kaz

0.15

orp

0.14

olin

0.14

Activations Density 0.030%

terms related to exemptions and exceptions in regulations or laws

No Comments

No Known Activations