INDEX

Explanations

numerical data points and their relevance to key concepts and trends

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

outers

-0.15

Ã³ng

-0.14

Ð»Ð¾Ð¿

-0.14

ÑĭÑĪ

-0.14

adamente

-0.14

ubar

-0.14

llib

-0.13

à¸ķà¸°

-0.13

å¯

-0.13

ÏĥÏĥ

-0.13

POSITIVE LOGITS

0.29

0.23

0.21

0.18

0.17

0.16

0.15

Activations Density 0.075%

numerical data points and their relevance to key concepts and trends

No Comments

No Known Activations