INDEX

Explanations

conversational phrases that directly engage the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ulfilled

-0.17

nerRadius

-0.17

æ¡Ĳ

-0.16

isode

-0.15

itary

-0.14

aminer

-0.14

urette

-0.14

ãģ£ãģ

-0.14

iazza

-0.14

Ð¾ÑģÑĤÑĸ

-0.14

POSITIVE LOGITS

uckle

0.14

atore

0.14

anye

0.14

ONY

0.14

0.13

.Expr

0.13

nger

0.13

rez

0.13

uj

0.13

Activations Density 0.145%

conversational phrases that directly engage the reader

No Comments

No Known Activations