INDEX

Explanations

instances of comparison between people or things, particularly highlighting contradictions or similarities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

æĹ¢çĦ¶

-0.14

errs

-0.13

 ÐºÐ¾Ð½ÐµÑĩÐ½Ð¾

-0.13

 ìĹŃìĭľ

-0.13

_globals

-0.13

rama

-0.13

lluminate

-0.13

åĺĽ

-0.13

 Obviously

-0.13

ayah

-0.13

POSITIVE LOGITS

 practically

0.35

 literally

0.31

 almost

0.30

 barely

0.30

 downright

0.30

 virtually

0.29

 nearly

0.28

 scarcely

0.28

 border

0.27

 verg

0.26

Activations Density 0.531%

instances of comparison between people or things, particularly highlighting contradictions or similarities

No Comments

No Known Activations