INDEX

Explanations

medical terms related to viral infections and immunization 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

Î¼Î·

-0.14

 repell

-0.14

keley

-0.13

ãĥĸãĥŃ

-0.13

leys

-0.13

Ø§ÙĦÙĬØ©

-0.13

 poisoned

-0.13

ffer

-0.13

 Sanctuary

-0.13

fty

-0.13

POSITIVE LOGITS

 strains

0.18

 opportun

0.17

 viruses

0.17

ivirus

0.17

 virus

0.16

Inflater

0.16

ehr

0.16

 strain

0.15

 Flex

0.15

Envelope

0.15

Activations Density 0.178%

medical terms related to viral infections and immunization discussions

No Comments

No Known Activations