INDEX

Explanations

references to "Apple" and its products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

naire

-0.20

furt

-0.17

spb

-0.17

enor

-0.16

naires

-0.15

elor

-0.15

liest

-0.15

yon

-0.15

emaker

-0.15

ften

-0.15

POSITIVE LOGITS

 cider

0.26

baum

0.25

bee

0.23

ton

0.21

auce

0.21

jack

0.20

seed

0.19

/apple

0.18

tons

0.18

 orch

0.17

Activations Density 0.012%

references to "Apple" and its products or services

No Comments

No Known Activations