INDEX

Explanations

words and phrases related to honor and recognition

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

sian

-0.17

gere

-0.16

PT

-0.16

íĻľ

-0.15

urge

-0.15

endencies

-0.15

-0.14

fÃ¼h

-0.14

ya

-0.14

 automÃ¡ticamente

-0.14

POSITIVE LOGITS

ably

0.29

ific

0.19

able

0.18

ment

0.17

full

0.16

ABLE

0.16

ise

0.15

/dis

0.14

orable

0.14

exion

0.14

Activations Density 0.038%

words and phrases related to honor and recognition

No Comments

No Known Activations