INDEX

Explanations

technical terms and keywords related to programming and data structure manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 creative

-0.14

creative

-0.14

iol

-0.14

ux

-0.14

Surname

-0.13

ÅĤaw

-0.13

ALAR

-0.13

te

-0.13

cestor

-0.13

ldb

-0.13

POSITIVE LOGITS

ueva

0.15

ìĦ¸ëĮĢ

0.14

arkin

0.14

åĪ¶

0.14

dee

0.14

0.13

 Ø±Ø³Ùħ

0.13

ESCO

0.13

.song

0.13

ĸ

0.13

Activations Density 0.049%

technical terms and keywords related to programming and data structure manipulation

No Comments

No Known Activations