INDEX

Explanations

references to significant historical figures and their quotes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

and

-0.15

 next

-0.15

 which

-0.15

Æ°Æ¡ng

-0.15

 instead

-0.15

 opposite

-0.14

ounced

-0.14

ogh

-0.14

Clo

-0.13

kÄĻ

-0.13

POSITIVE LOGITS

quoted

0.26

 quoted

0.25

 quote

0.21

 Quotes

0.19

-quote

0.19

æĳĺ

0.18

 paraph

0.18

 quotes

0.18

_quote

0.17

 quoting

0.17

Activations Density 0.068%

references to significant historical figures and their quotes

No Comments

No Known Activations