INDEX

Explanations

references to motorsport events and related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abus

-0.19

idy

-0.15

Ã¢n

-0.15

æĸ¹

-0.15

Ä±rak

-0.14

ancell

-0.14

 ADVISED

-0.14

idlo

-0.14

DisplayStyle

-0.14

.XPath

-0.14

POSITIVE LOGITS

 Bath

0.28

 Hold

0.24

 Holden

0.23

Sup

0.23

 hold

0.21

Hold

0.19

 Clips

0.19

Ere

0.19

 HOLD

0.18

 bath

0.17

Activations Density 0.009%

references to motorsport events and related activities

No Comments

No Known Activations