INDEX

Explanations

references to locations, specifically those related to New York

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

paren

-0.18

yi

-0.17

lem

-0.17

wei

-0.16

ray

-0.15

ncia

-0.15

yal

-0.15

 cÃ¢n

-0.14

cntl

-0.14

yms

-0.14

POSITIVE LOGITS

quist

0.26

bble

0.21

QUI

0.19

times

0.18

NÃį

0.18

ny

0.17

Ny

0.17

borg

0.17

IAS

0.17

umba

0.17

Activations Density 0.013%

references to locations, specifically those related to New York

No Comments

No Known Activations