INDEX

Explanations

phrases indicating significant projects or collaborative efforts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

anggan

-0.16

ç«ĭãģ¦

-0.15

 invented

-0.15

åĭĩ

-0.15

onent

-0.14

ENTIAL

-0.13

æŃ¢

-0.13

/notification

-0.13

Ð¾ÐºÐ°

-0.13

Gs

-0.13

POSITIVE LOGITS

 months

0.25

 effort

0.20

 spent

0.20

 culmination

0.19

 hours

0.19

 Work

0.18

 team

0.18

months

0.17

 process

0.17

cul

0.17

Activations Density 0.317%

phrases indicating significant projects or collaborative efforts

No Comments

No Known Activations