INDEX

Explanations

technical programming terms and metrics related to code structure and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

er

-0.18

ÏģÎ¿Î¹

-0.15

 UNUSED

-0.14

 Lawn

-0.14

oloj

-0.14

erap

-0.14

áº¯p

-0.13

enga

-0.13

bla

-0.13

aco

-0.13

POSITIVE LOGITS

ForegroundColor

0.14

FY

0.14

enty

0.14

acional

0.14

ħn

0.14

ICODE

0.14

ÃĿ

0.13

ç½

0.13

ØºØ§ÙĦ

0.13

Activations Density 0.028%

technical programming terms and metrics related to code structure and functions

No Comments

No Known Activations