INDEX

Explanations

references to individuals and individualism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

dden

-0.17

Ú¯Ø§Ùĩ

-0.16

Ð½Ð´

-0.16

ëģĶ

-0.15

 majority

-0.15

bulan

-0.14

ArgumentException

-0.14

own

-0.14

ylon

-0.13

IDEO

-0.13

POSITIVE LOGITS

ized

0.26

itarian

0.21

/group

0.21

itÃ©s

0.20

/groups

0.20

/team

0.20

ize

0.20

ity

0.19

hood

0.19

/single

0.18

Activations Density 0.029%

references to individuals and individualism

No Comments

No Known Activations