INDEX

Explanations

terms related to health, well-being, and their management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

.IContainer

-0.17

istrovstvÃŃ

-0.17

ydk

-0.16

¶ģ

-0.15

orna

-0.14

ulling

-0.14

achat

-0.14

GRA

-0.14

acket

-0.14

.za

-0.14

POSITIVE LOGITS

osh

0.18

 sense

0.17

OSH

0.16

“

0.15

 organ

0.15

itom

0.14

 Leone

0.14

Activations Density 0.151%

terms related to health, well-being, and their management

No Comments

No Known Activations