INDEX

Explanations

timestamps and numerical data within the document

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

Lov

-0.17

ennes

-0.14

aÄŁÄ±

-0.14

strate

-0.14

ÑĥÑĪ

-0.14

auf

-0.14

 expelled

-0.14

bulan

-0.13

 knobs

-0.13

 perish

-0.13

POSITIVE LOGITS

à¸²à¸¡

0.16

 Colbert

0.15

QRST

0.15

indre

0.14

itzer

0.14

igham

0.14

 broad

0.14

0.13

Activations Density 0.208%

timestamps and numerical data within the document

No Comments

No Known Activations