INDEX

Explanations

punctuation marks and variations in their frequency

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

odore

-0.23

ah

-0.16

ummer

-0.15

 Ð¶Ðµ

-0.15

-ÑĤÐ°ÐºÐ¸

-0.14

iry

-0.14

allee

-0.14

usty

-0.13

xiety

-0.13

uzzle

-0.13

POSITIVE LOGITS

0.17

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

0.17

 latter

0.16

phans

0.16

,,,

0.16

loor

0.15

,,,,,,,,

0.15

cgi

0.15

ylland

0.14

ska

0.14

Activations Density 0.105%

punctuation marks and variations in their frequency

No Comments

No Known Activations