INDEX

Explanations

terms related to cancer research and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

rna

-0.15

å·»

-0.15

ofile

-0.15

upe

-0.15

 infect

-0.15

 infectious

-0.14

Ð´ÑĸÐ»

-0.14

oux

-0.14

isy

-0.14

á»ĩ

-0.14

POSITIVE LOGITS

 arom

0.33

 estr

0.32

 prog

0.32

 testosterone

0.31

 Estr

0.29

prog

0.27

 estrogen

0.27

 endors

0.26

estr

0.26

 follic

0.26

Activations Density 0.025%

terms related to cancer research and treatments

No Comments

No Known Activations