INDEX

Explanations

segments of code and programming-related syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 compliment

-0.17

ead

-0.16

ilst

-0.16

ft

-0.15

-0.14

 seper

-0.14

arger

-0.14

éħ

-0.14

ander

-0.14

 backwards

-0.14

POSITIVE LOGITS

 nons

0.19

rawer

0.17

-plus

0.15

 ØªÙĪØ³

0.15

Ð¾Ð¿Ð¸Ñģ

0.15

engl

0.14

cko

0.14

Ã¼Ã§Ã¼k

0.14

"'

0.14

thew

0.13

Activations Density 1.182%

segments of code and programming-related syntax

No Comments

No Known Activations