INDEX

Explanations

references to the University of Oxford and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

odd

-0.16

Äįet

-0.15

ÎŃÏģÎ³

-0.15

NewLabel

-0.14

ighted

-0.14

uru

-0.14

 Danh

-0.14

anke

-0.14

ypse

-0.14

omor

-0.14

POSITIVE LOGITS

shire

0.33

 University

0.25

 Companion

0.19

Bro

0.19

 university

0.19

University

0.18

 Isis

0.17

 UNIVERSITY

0.16

 comma

0.16

Uni

0.16

Activations Density 0.008%

references to the University of Oxford and related terms

No Comments

No Known Activations