INDEX

Explanations

references to data and databases in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

_data

-0.24

Data

-0.23

Datas

-0.20

_datas

-0.20

 data

-0.20

 Data

-0.20

data

-0.19

TestData

-0.19

æķ°æį®

-0.19

dat

-0.19

POSITIVE LOGITS

 sets

0.33

 collection

0.29

streams

0.28

 points

0.28

-points

0.28

 collected

0.28

-collection

0.27

files

0.27

collection

0.26

flow

0.25

Activations Density 0.049%

references to data and databases in various contexts

No Comments

No Known Activations