INDEX

Explanations

references to technical issues or troubleshooting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ecta

-0.16

Pek

-0.15

achts

-0.14

LLP

-0.14

efined

-0.14

ARB

-0.14

 Mezi

-0.14

iska

-0.14

Consumer

-0.14

æ·

-0.14

POSITIVE LOGITS

 Cisco

0.23

Cisco

0.22

ydk

0.18

IOS

0.16

 Palo

0.16

.opendaylight

0.16

osit

0.15

.yang

0.15

oxid

0.15

assis

0.15

Activations Density 0.015%

references to technical issues or troubleshooting

No Comments

No Known Activations