INDEX

Explanations

technical terms and operations related to database queries and data manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ober

-0.16

argo

-0.15

èĻ

-0.15

ãĥ³ãĥĲ

-0.14

çŀ

-0.14

 domestic

-0.14

ICODE

-0.13

FindBy

-0.13

ioni

-0.13

otti

-0.13

POSITIVE LOGITS

 Ø·ÙĦ

0.18

WARDS

0.16

ãĤ¢ãĥ¼

0.15

-Jul

0.15

AAD

0.14

URITY

0.14

HQ

0.14

usercontent

0.14

.ie

0.13

DMI

0.13

Activations Density 0.232%

technical terms and operations related to database queries and data manipulation

No Comments

No Known Activations