INDEX

Explanations

references to machine learning and artificial intelligence technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

illos

-0.17

ynch

-0.15

atti

-0.15

ITES

-0.15

 IOCTL

-0.14

ãĥĥãĤ«ãĥ¼

-0.14

 Thornton

-0.14

silver

-0.14

deme

-0.14

epad

-0.14

POSITIVE LOGITS

 learning

0.27

 Learning

0.25

-readable

0.24

Learning

0.24

 readable

0.24

-learning

0.23

-machine

0.22

learning

0.21

.machine

0.21

 vision

0.21

Activations Density 0.010%

references to machine learning and artificial intelligence technologies

No Comments

No Known Activations