INDEX

Explanations

mathematical symbols and numeric values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ovan

-0.17

Äįe

-0.16

ç´

-0.15

olin

-0.15

etch

-0.15

alin

-0.15

etÃŃ

-0.14

omet

-0.14

lich

-0.14

ElementsByTagName

-0.14

POSITIVE LOGITS

 absorbed

0.16

ason

0.15

 absorption

0.15

 Margaret

0.15

scores

0.15

 Meaning

0.15

hat

0.15

xab

0.14

 Mason

0.14

Hat

0.14

Activations Density 0.006%

mathematical symbols and numeric values

No Comments

No Known Activations