INDEX

Explanations

numbers, particularly dates and statistics

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

olon

-0.14

 Pale

-0.13

orc

-0.13

á»Ł

-0.13

 subt

-0.13

aru

-0.13

id

-0.13

ic

-0.13

POSITIVE LOGITS

ÙĨØ§Ùħ

0.16

 pylint

0.16

ä»½

0.15

ujet

0.15

à¥°

0.15

rades

0.15

jez

0.14

/goto

0.14

.updateDynamic

0.14

phis

0.14

Activations Density 0.074%

numbers, particularly dates and statistics

No Comments

No Known Activations