INDEX

Explanations

specific product names and brands related to goods and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ka

-0.31

che

-0.24

li

-0.23

pro

-0.23

bo

-0.23

ben

-0.23

il

-0.22

nya

-0.21

va

-0.21

bas

-0.21

POSITIVE LOGITS

Ùĭ

0.27

’nÄ±n

0.25

'nÄ±n

0.24

eus

0.24

issance

0.23

ught

0.23

ein

0.22

ugh

0.22

flow

0.21

erts

0.21

Activations Density 1.031%

specific product names and brands related to goods and events

No Comments

No Known Activations

specific product names and brands related to goods and events

No Comments

No Known Activations