INDEX

Explanations

references to streaming processes or commands in programming

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

uster

-0.18

Ã¡no

-0.17

ortal

-0.16

osten

-0.15

 Shared

-0.15

rust

-0.14

owers

-0.14

ÐºÐ¾Ð·

-0.14

èĬĿ

-0.14

enou

-0.14

POSITIVE LOGITS

æİĴ

0.16

iev

0.15

 whom

0.15

 Perr

0.14

è¾

0.14

ÃĹ↵↵

0.14

 rollback

0.14

/arch

0.13

 cáº¥p

0.13

 QuÃ©

0.13

Activations Density 0.000%

references to streaming processes or commands in programming

No Comments

No Known Activations