INDEX

Explanations

references to years, dates, and specific numeric data points related to events or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Ð²Ð¾ÑĤ

-0.14

agues

-0.14

ĵĺ

-0.14

ancode

-0.14

ritt

-0.14

odon

-0.13

 Rust

-0.13

ila

-0.13

odo

-0.13

ëĿ¼ëıĦ

-0.13

POSITIVE LOGITS

0.16

Ã¢h

0.15

0.14

 flyer

0.14

èİİ

0.14

markup

0.14

 Zion

0.13

emi

0.13

Activations Density 0.026%

references to years, dates, and specific numeric data points related to events or organizations

No Comments

No Known Activations