INDEX

Explanations

regulatory and legal language related to privacy and securities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ange

-0.15

mitt

-0.15

awy

-0.14

Ã¢ce

-0.14

asar

-0.14

ork

-0.14

 Tanner

-0.13

 Vand

-0.13

cheme

-0.13

 Kiss

-0.13

POSITIVE LOGITS

 DAMAGES

0.17

rypton

0.15

ulse

0.15

APSHOT

0.14

smarty

0.14

 \č↵

0.14

yal

0.14

 ç¨

0.13

gnore

0.13

Activations Density 0.065%

regulatory and legal language related to privacy and securities

No Comments

No Known Activations