INDEX

Explanations

coding functions and measures related to performance tracking in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Ratings

-0.14

onna

-0.14

immers

-0.14

 Ð½Ð°Ð·Ð½Ð°Ñĩ

-0.13

 accommodations

-0.13

Ð¾Ð¿Ð°Ñģ

-0.13

iland

-0.13

 Weekly

-0.13

ÙħØ§Ùħ

-0.13

sworth

-0.13

POSITIVE LOGITS

 benchmark

0.32

benchmark

0.29

 times

0.29

 timing

0.28

 bench

0.27

bench

0.27

Benchmark

0.27

 benchmarks

0.26

 Benchmark

0.26

 Bench

0.26

Activations Density 0.060%

coding functions and measures related to performance tracking in programming

No Comments

No Known Activations