INDEX

Explanations

terms related to viruses and epidemics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ipp

-0.15

æ¼¢

-0.15

tie

-0.15

cona

-0.14

asher

-0.14

urf

-0.14

yon

-0.13

ãĤıãģŁãģĹ

-0.13

ione

-0.13

averse

-0.13

POSITIVE LOGITS

leta

0.14

 Ð±Ð¾ÑĢ

0.14

Łèĥ½

0.14

">ÃĹ</

0.14

Ø§ÙĦØ¯

0.13

-scripts

0.13

meli

0.13

 Burnett

0.13

ovel

0.13

ÙģÙĦ

0.13

Activations Density 0.070%

terms related to viruses and epidemics

No Comments

No Known Activations