INDEX

Explanations

references to music releases and album details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

icals

-0.15

 Kirby

-0.14

bart

-0.14

cod

-0.14

 author

-0.14

engo

-0.14

elts

-0.13

ifu

-0.13

omez

-0.13

oder

-0.13

POSITIVE LOGITS

 Records

0.35

 label

0.32

 records

0.30

 labels

0.29

 Label

0.29

 record

0.27

 Labels

0.27

Records

0.27

records

0.26

-label

0.25

Activations Density 0.084%

references to music releases and album details

No Comments

No Known Activations