INDEX

Explanations

references to health-related research and discussions

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

weathermap

-0.17

Aliases

-0.14

abs

-0.14

 ÎķÎ¾

-0.14

_face

-0.13

ì°°

-0.13

 tháº¥t

-0.13

Disappear

-0.13

pdb

-0.13

bic

-0.13

POSITIVE LOGITS

 carcin

0.37

 cancer

0.28

 Cancer

0.26

 cancers

0.24

tum

0.24

DNA

0.23

 tumors

0.23

mut

0.22

 tumor

0.20

 carcinoma

0.19

Activations Density 0.061%

references to health-related research and discussions

No Comments

No Known Activations