INDEX

Explanations

abbreviations and acronyms related to organizations, technical terms, and specific entities

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

edException

-0.18

.googleapis

-0.17

aub

-0.17

eding

-0.15

athan

-0.15

iyle

-0.15

illez

-0.15

flix

-0.15

izer

-0.15

anz

-0.14

POSITIVE LOGITS

teenth

0.24

ê¹

0.21

patrick

0.18

zelf

0.18

åĪ»

0.17

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

0.17

ylland

0.17

ellaneous

0.16

zsche

0.16

abeth

0.16

Activations Density 0.431%

abbreviations and acronyms related to organizations, technical terms, and specific entities

No Comments

No Known Activations