INDEX

Explanations

references to page numbers in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

rem

-0.18

ship

-0.16

series

-0.16

self

-0.16

roy

-0.16

Ø§ÙĪÙĬØ©

-0.15

ly

-0.15

road

-0.15

sole

-0.15

 Baths

-0.15

POSITIVE LOGITS

antry

0.35

ant

0.27

views

0.26

-turn

0.21

çľī

0.20

/post

0.19

peed

0.19

-load

0.18

Rank

0.18

pole

0.18

Activations Density 0.041%

references to page numbers in a document

No Comments

No Known Activations