INDEX

Explanations

instances of the word "yet," indicating uncertainty or the idea of something that has not happened or been determined

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 overnight

-0.16

er

-0.16

eza

-0.15

ATALOG

-0.15

/py

-0.15

ila

-0.15

richt

-0.15

ady

-0.14

ess

-0.14

ulas

-0.14

POSITIVE LOGITS

tings

0.16

taj

0.15

kowski

0.15

Ãºsqueda

0.15

lingen

0.15

arring

0.14

Î¹

0.14

 ë²Īì§¸

0.14

theless

0.14

rek

0.14

Activations Density 0.022%

instances of the word "yet," indicating uncertainty or the idea of something that has not happened or been determined

No Comments

No Known Activations