INDEX

Explanations

patterns related to cycles and repetitions in processes or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

imas

-0.16

.createObject

-0.15

esini

-0.15

 progressing

-0.14

ÑĮÐ¼Ð¸

-0.14

 Leban

-0.14

swick

-0.14

endas

-0.14

 Scri

-0.14

finally

-0.13

POSITIVE LOGITS

 again

0.31

again

0.25

 next

0.25

 Again

0.24

Again

0.22

next

0.22

_again

0.21

 lagi

0.20

 wieder

0.19

 ëĭ¤ìĭľ

0.19

Activations Density 0.239%

patterns related to cycles and repetitions in processes or events

No Comments

No Known Activations