INDEX

Explanations

comparisons involving numerical data and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

higher

-0.16

stry

-0.15

 higher

-0.15

omu

-0.15

,...↵↵

-0.15

Higher

-0.15

,application

-0.14

Å¾it

-0.14

íģ

-0.14

suspend

-0.14

POSITIVE LOGITS

 only

0.30

 smaller

0.26

 mere

0.26

 fewer

0.25

 less

0.24

 merely

0.24

 apenas

0.23

 Only

0.22

only

0.22

Only

0.21

Activations Density 0.109%

comparisons involving numerical data and performance metrics

No Comments

No Known Activations