INDEX

Explanations

references to lines of code and their related contexts in programming discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

rea

-0.16

dba

-0.15

éģ

-0.15

cha

-0.14

BA

-0.14

 upside

-0.14

-0.13

Bo

-0.13

Î½ÏĦ

-0.13

POSITIVE LOGITS

Ðİ

0.16

aviest

0.16

utow

0.16

ç®

0.15

Ð»Ð¸Ð½

0.15

ãģĲ

0.15

eced

0.15

ulse

0.15

ervo

0.15

íĻľ

0.14

Activations Density 0.050%

references to lines of code and their related contexts in programming discussions

No Comments

No Known Activations