INDEX

Explanations

a variety of event-related functions and properties in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 GOODMAN

-0.18

omik

-0.17

icer

-0.16

Î½Î¿Ïį

-0.16

haar

-0.15

odyn

-0.15

AFX

-0.15

esto

-0.15

ç´ļ

-0.14

yslu

-0.14

POSITIVE LOGITS

 Dwarf

0.16

orgot

0.15

ĴĮ

0.14

oren

0.14

ridge

0.14

ITTE

0.13

 Copp

0.13

Ø§Ø¡Ø§Øª

0.13

 alias

0.13

 whole

0.13

Activations Density 0.158%

a variety of event-related functions and properties in code

No Comments

No Known Activations