INDEX

Explanations

phrases related to privacy and data protection practices

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

 Grove

-0.16

 Moss

-0.15

olib

-0.15

 Prosper

-0.15

Haz

-0.14

@$

-0.14

wy

-0.14

Ø§ÙĦÙĬØ§

-0.13

ise

-0.13

 Agricultural

-0.13

POSITIVE LOGITS

0.18

ijd

0.15

eyJ

0.15

rej

0.15

ilim

0.15

andel

0.14

ettel

0.14

 Ä±s

0.14

ÐµÐ³Ð¾ÑĢ

0.14

ndo

0.14

Activations Density 0.028%

phrases related to privacy and data protection practices

No Comments

No Known Activations