INDEX

Explanations

references to specific time periods and significant decades throughout history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 tiener

-0.17

ause

-0.17

 McMahon

-0.16

olie

-0.15

ubber

-0.14

Ð»Ñĥ

-0.14

áº«

-0.14

kinson

-0.14

izon

-0.14

utan

-0.14

POSITIVE LOGITS

 century

0.22

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.20

era

0.18

-century

0.17

/post

0.16

 itself

0.16

cent

0.15

Launcher

0.15

era

0.15

Ã½n

0.15

Activations Density 0.016%

references to specific time periods and significant decades throughout history

No Comments

No Known Activations