INDEX

Explanations

variations of the word "globe."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

agara

-0.18

">ÃĹ</

-0.17

itou

-0.16

avra

-0.16

hips

-0.16

zelf

-0.15

orns

-0.15

ë§ī

-0.15

&action

-0.15

iero

-0.14

POSITIVE LOGITS

.glob

0.28

ally

0.22

 trot

0.22

 Trot

0.22

 warming

0.20

ular

0.20

 globe

0.19

glo

0.19

/local

0.18

 glob

0.17

Activations Density 0.008%

variations of the word "globe."

No Comments

No Known Activations