INDEX

Explanations

references to legal requests and governmental transparency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

pow

-0.16

(describing

-0.15

 ç²

-0.14

 mitt

-0.14

icha

-0.14

 Borg

-0.14

èº

-0.14

ÏĢÎ¿ÏĤ

-0.14

 loyal

-0.14

izz

-0.13

POSITIVE LOGITS

FO

0.39

 Freedom

0.31

FO

0.27

Freedom

0.27

 requester

0.23

 freedom

0.22

 request

0.22

PIO

0.21

 requests

0.20

Fo

0.20

Activations Density 0.036%

references to legal requests and governmental transparency

No Comments

No Known Activations