INDEX

Explanations

high-frequency definite articles and the corresponding context in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Yen

-0.16

ppe

-0.16

nell

-0.16

igne

-0.15

uria

-0.15

fen

-0.15

 Peer

-0.15

apan

-0.15

ML

-0.14

efa

-0.14

POSITIVE LOGITS

loff

0.16

oldem

0.15

 Boulder

0.14

emez

0.14

 locus

0.14

inki

0.14

_BACKEND

0.14

 Skyl

0.13

 probable

0.13

Activations Density 0.300%

high-frequency definite articles and the corresponding context in documents

No Comments

No Known Activations