INDEX

Explanations

updates about new features and events related to a service or platform

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

ince

-0.14

iface

-0.14

 ?↵↵

-0.14

æĨ¶

-0.13

 .↵↵

-0.13

á»įt

-0.13

 Bliss

-0.13

ï¼Ł↵

-0.12

ÐµÑĢÐ°

-0.12

 ,↵↵

-0.12

POSITIVE LOGITS

our

0.28

0.20

our

0.20

æĪĳä»¬çļĦ

0.17

 your

0.17

 exciting

0.17

 ourselves

0.16

 nostro

0.15

 nosso

0.15

 yourselves

0.15

Activations Density 0.504%

updates about new features and events related to a service or platform

No Comments

No Known Activations