INDEX

Explanations

instances of the word "honor" and its variations, indicating a focus on themes of respect and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ENDOR

-0.17

.scalablytyped

-0.17

nesia

-0.16

ŀæĢ§

-0.16

bage

-0.15

lenÃŃ

-0.15

SupportedContent

-0.15

roupe

-0.15

ÑĤÐ¸Ð²

-0.14

oje

-0.14

POSITIVE LOGITS

ymoon

0.20

orary

0.20

olulu

0.20

ym

0.17

blas

0.17

obox

0.16

ycastle

0.16

ight

0.16

 Milan

0.16

esty

0.15

Activations Density 0.013%

instances of the word "honor" and its variations, indicating a focus on themes of respect and recognition

No Comments

No Known Activations