INDEX

Explanations

information related to access control and security issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 erst

-0.19

nick

-0.16

 Shiv

-0.16

Rug

-0.14

umba

-0.13

ensch

-0.13

eer

-0.13

etti

-0.13

iotic

-0.13

 Shoe

-0.13

POSITIVE LOGITS

 existed

0.18

_para

0.17

jian

0.16

 ï¼ļ

0.15

ï¼ļ↵

0.15

.weixin

0.15

cac

0.15

uplicated

0.15

ï¼ļ

0.15

ipay

0.15

Activations Density 0.184%

information related to access control and security issues

No Comments

No Known Activations