INDEX

Explanations

references to COVID-19 and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

iring

-0.15

Î²Î¿Î»

-0.14

atinum

-0.14

ç½ļ

-0.14

istrovstvÃŃ

-0.13

warnings

-0.13

ubi

-0.13

eview

-0.13

-bodied

-0.13

ãĥªãĥ¼ãĤº

-0.13

POSITIVE LOGITS

0.19

UILayout

0.16

ongan

0.15

fat

0.15

æĥħ

0.15

istant

0.14

ienne

0.14

orners

0.14

DPI

0.14

cast

0.14

Activations Density 0.011%

references to COVID-19 and its variants

No Comments

No Known Activations