INDEX

Explanations

key legal and regulatory terminology related to compliance and restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

igned

-0.17

à¹ĩà¸Ķ

-0.15

 Skip

-0.15

box

-0.15

Nar

-0.15

rique

-0.14

ATRIX

-0.14

èµĸ

-0.14

 Dare

-0.14

adow

-0.14

POSITIVE LOGITS

oot

0.20

amb

0.20

Amb

0.17

eld

0.16

ellung

0.15

Encoding

0.15

Inn

0.15

_normalized

0.15

diag

0.14

ys

0.14

Activations Density 0.013%

key legal and regulatory terminology related to compliance and restrictions

No Comments

No Known Activations