INDEX

Explanations

references to Columbia University

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ahl

-0.17

igo

-0.15

 collapses

-0.15

inus

-0.15

akk

-0.15

 Huffman

-0.14

abbo

-0.14

ova

-0.14

ERA

-0.14

POSITIVE LOGITS

 Columbia

0.44

olumbia

0.35

 Colum

0.29

 Colombia

0.28

 Barn

0.28

 Mail

0.24

SIP

0.23

 Teachers

0.22

 colum

0.21

Lam

0.21

Activations Density 0.011%

references to Columbia University

No Comments

No Known Activations