INDEX

Explanations

references to total amounts or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

etta

-0.20

ett

-0.19

roe

-0.17

ette

-0.17

ess

-0.16

ettes

-0.14

andi

-0.13

ç«ĭãģ¦

-0.13

.SwingConstants

-0.13

OR

-0.13

POSITIVE LOGITS

ted

0.16

iseum

0.16

izing

0.15

itÃ©

0.15

izando

0.15

zv

0.15

 Boeh

0.14

ateral

0.14

buquerque

0.14

ĭ

0.14

Activations Density 0.023%

references to total amounts or quantities

No Comments

No Known Activations