INDEX

Explanations

references to events or workshops focused on community and personal development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

owns

-0.15

 various

-0.14

iles

-0.13

iled

-0.13

onica

-0.13

ord

-0.13

OST

-0.12

arr

-0.12

ened

-0.12

Did

-0.12

POSITIVE LOGITS

is

0.32

æĺ¯ä¸Ģä¸ª

0.25

æĺ¯æĪĳ

0.23

æĺ¯ä¸Ģ

0.21

 ÑıÐ²Ð»ÑıÐµÑĤÑģÑı

0.20

 adalah

0.19

isn

0.19

was

0.19

 æĺ¯

0.19

æĺ¯ä¸ª

0.18

Activations Density 0.126%

references to events or workshops focused on community and personal development

No Comments

No Known Activations