INDEX

Explanations

connections to popular brands or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

one

-0.14

allery

-0.14

onec

-0.13

 grantResults

-0.13

into

-0.13

itol

-0.13

Ø²Ùĩ

-0.13

istrovstvÃŃ

-0.13

zp

-0.12

haul

-0.12

POSITIVE LOGITS

etc

0.27

etc

0.26

 others

0.25

 Others

0.18

 ÑĤÐ¾ÑīÐ¾

0.18

others

0.17

ãģĿãģĹãģ¦

0.17

 ÙĪØºÙĬØ±

0.16

 hatta

0.16

 among

0.16

Activations Density 0.616%

connections to popular brands or products

No Comments

No Known Activations