INDEX

Explanations

keywords related to performance metrics and unsuccessful outcomes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

inth

-0.15

inha

-0.14

Ð¾Ð±Ð¸

-0.13

 alanda

-0.13

çīĮ

-0.13

 spor

-0.13

eldo

-0.13

istrovstvÃŃ

-0.13

reib

-0.13

 touring

-0.13

POSITIVE LOGITS

 experiment

0.36

 visit

0.35

 session

0.34

 trip

0.34

 encounter

0.34

 experience

0.30

 event

0.30

 move

0.29

 episode

0.29

 transaction

0.28

Activations Density 0.155%

keywords related to performance metrics and unsuccessful outcomes in various contexts

No Comments

No Known Activations