INDEX

Explanations

mentions of COVID-19 variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

arella

-0.16

»

-0.15

hsi

-0.15

.scalablytyped

-0.15

Shell

-0.14

byn

-0.14

pedia

-0.14

bis

-0.14

Ø¯ÙĪØ¯

-0.14

ÐµÐ²Ñĸ

-0.13

POSITIVE LOGITS

 strain

0.39

 variant

0.37

 Variant

0.35

 variants

0.33

 strains

0.31

variant

0.29

Variant

0.29

strain

0.28

 mutation

0.25

 mutations

0.25

Activations Density 0.008%

mentions of COVID-19 variants

No Comments

No Known Activations