INDEX

Explanations

terms and discussions related to COVID-19 and immunity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 addCriterion

-0.18

.onView

-0.16

ohn

-0.15

isle

-0.14

assin

-0.14

CISION

-0.14

epar

-0.14

cona

-0.14

otta

-0.14

Ã±os

-0.13

POSITIVE LOGITS

0.16

ADE

0.15

 diss

0.14

rip

0.14

yet

0.14

Elk

0.14

usi

0.14

 reservoir

0.14

Activations Density 0.111%

terms and discussions related to COVID-19 and immunity

No Comments

No Known Activations