INDEX

Explanations

references to various types of licenses and roles within organizations

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

'gc

-0.16

bau

-0.15

AVA

-0.15

 hang

-0.14

.ReadFile

-0.14

zel

-0.14

.Fail

-0.14

Hang

-0.13

äº

-0.13

stad

-0.13

POSITIVE LOGITS

unp

0.16

kin

0.15

iode

0.15

oth

0.14

AppName

0.14

evi

0.14

 Watkins

0.14

 springfox

0.14

MaxLength

0.14

OptionPane

0.14

Activations Density 0.811%

references to various types of licenses and roles within organizations

No Comments

No Known Activations