INDEX

Explanations

specific proper nouns and names related to individuals or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ÃĹ↵↵

-0.15

xd

-0.15

rav

-0.15

iec

-0.15

 Glide

-0.14

Ñĳ

-0.14

ÑĤÐ¸Ðº

-0.14

Î¼Î¯

-0.14

ÑĢÐ°Ð²

-0.14

/licenses

-0.13

POSITIVE LOGITS

Ã¼ml

0.14

allet

0.14

ellas

0.14

å®Ļ

0.14

 Elephant

0.14

 Patel

0.13

aco

0.13

endant

0.13

inks

0.13

à¸Ļà¹ĥà¸Ī

0.13

Activations Density 0.249%

specific proper nouns and names related to individuals or organizations

No Comments

No Known Activations