INDEX

Explanations

technical terms and phrases related to algorithms and analysis in computer science and data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

metic

-0.16

allo

-0.15

.Dto

-0.15

Î»Î¿Ïħ

-0.15

ocode

-0.14

stroy

-0.14

 cres

-0.14

ESSAGES

-0.14

ãĥģãĥ¥

-0.14

bote

-0.14

POSITIVE LOGITS

0.16

0.15

aim

0.15

ond

0.15

ony

0.15

ØªØ¯Ùī

0.14

sil

0.14

onda

0.14

oda

0.14

Activations Density 0.104%

technical terms and phrases related to algorithms and analysis in computer science and data processing

No Comments

No Known Activations