INDEX

Explanations

technical terminology and concepts related to programming and data management

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

 Koch

-0.17

heimer

-0.16

 åł

-0.15

Lau

-0.14

.gms

-0.14

 JetBrains

-0.14

iju

-0.13

coholic

-0.13

iedo

-0.12

 Tower

-0.12

POSITIVE LOGITS

RDF

0.39

rdf

0.39

owl

0.35

 triples

0.35

OWL

0.34

.rdf

0.33

rdf

0.33

 ontology

0.31

/owl

0.30

owl

0.30

Activations Density 0.034%

technical terminology and concepts related to programming and data management

No Comments

No Known Activations