INDEX

Explanations

programming-related code structures 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

eny

-0.15

ä¸´

-0.14

 radi

-0.14

squeeze

-0.14

 automated

-0.13

ushman

-0.13

 densities

-0.13

 Ð´ÑĢÐ°

-0.13

emax

-0.13

 station

-0.13

POSITIVE LOGITS

 time

0.22

 clock

0.21

 Time

0.20

.time

0.20

Performance

0.19

 measure

0.19

 Performance

0.19

 stopwatch

0.19

 Perf

0.18

 measuring

0.18

Activations Density 0.071%

programming-related code structures and performance metrics

No Comments

No Known Activations