INDEX

Explanations

terms and concepts related to programming languages and databases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

HeaderCode

-0.17

.myapplication

-0.15

INavigation

-0.14

_regeneration

-0.14

è¦§

-0.14

qli

-0.14

à¸¥à¸³

-0.14

SOFTWARE

-0.13

oracle

-0.13

hay

-0.13

POSITIVE LOGITS

>=

0.25

-based

0.24

>=

0.23

0.22

 itself

0.22

0.21

Activations Density 0.212%

terms and concepts related to programming languages and databases

No Comments

No Known Activations