INDEX

Explanations

sequential numerical data, specifically dates and scores

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Tra

-0.19

AGMA

-0.16

Enlarge

-0.15

kaar

-0.14

strcasecmp

-0.14

 ÑĤÐ¸Ð¼

-0.14

 ÑĥÑĩÐ°ÑģÑĤÐ¸

-0.14

íĨłíĨł

-0.13

ULONG

-0.13

POSITIVE LOGITS

strup

0.20

urg

0.17

illard

0.16

alace

0.15

hti

0.15

 distance

0.14

azzi

0.13

ë²½

0.13

mant

0.13

ami

0.13

Activations Density 0.002%

sequential numerical data, specifically dates and scores

No Comments

No Known Activations