INDEX

Explanations

punctuation and textual formatting elements that indicate pauses or interruptions

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

enek

-0.16

erah

-0.15

yah

-0.15

imet

-0.14

uela

-0.14

alog

-0.14

addir

-0.14

jang

-0.14

.addField

-0.13

ilog

-0.13

POSITIVE LOGITS

scratch

0.16

ucci

0.15

AFP

0.14

adol

0.14

 Exped

0.14

opsis

0.14

 ArgumentOutOfRangeException

0.13

iti

0.13

emos

0.13

tw

0.13

Activations Density 0.011%

punctuation and textual formatting elements that indicate pauses or interruptions

No Comments

No Known Activations