INDEX

Explanations

references to financial results and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

eki

-0.17

.labelX

-0.15

edla

-0.15

affen

-0.15

rex

-0.15

hiba

-0.15

imdi

-0.15

WidgetItem

-0.14

eczy

-0.14

Ðİ

-0.14

POSITIVE LOGITS

 being

0.39

being

0.34

 Being

0.27

Being

0.27

 sendo

0.26

è¢«

0.21

 essere

0.20

 having

0.19

-being

0.19

 becoming

0.18

Activations Density 0.154%

references to financial results and awards

No Comments

No Known Activations