INDEX

Explanations

occurrences of the term "COVID-19."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

anmar

-0.15

Ðİ

-0.15

erv

-0.14

ges

-0.14

[color

-0.14

ressive

-0.13

ammad

-0.13

aret

-0.13

erosis

-0.13

shint

-0.13

POSITIVE LOGITS

ï¸ı

0.17

oust

0.15

DirectoryName

0.15

Ø¯ÙĩÙħ

0.15

ereum

0.14

 Bloss

0.14

ÑĩÐ°ÑĤ

0.14

esModule

0.14

ases

0.13

Ø¯Ùĩ

0.13

Activations Density 0.011%

occurrences of the term "COVID-19."

No Comments

No Known Activations