INDEX

Explanations

references to medical diagnoses and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ensex

-0.15

nees

-0.14

å¦ĸ

-0.14

DeviceInfo

-0.14

 Ð¾ÑĤÐ´

-0.14

moil

-0.14

 nÃ¦r

-0.13

 urine

-0.13

RTC

-0.13

_CLICKED

-0.13

POSITIVE LOGITS

 Huntington

0.28

 Duch

0.27

Cro

0.26

 Parkinson

0.26

 Down

0.24

Eh

0.24

 Pompe

0.23

 terminal

0.22

 progressive

0.21

 incur

0.21

Activations Density 0.238%

references to medical diagnoses and conditions

No Comments

No Known Activations