INDEX

Explanations

references to digital media and graphic design elements

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

åĦ

-0.17

orthand

-0.15

amber

-0.15

 Hubb

-0.14

azio

-0.14

irim

-0.14

 Karlov

-0.13

 civil

-0.13

Formatter

-0.13

 McCarthy

-0.13

POSITIVE LOGITS

 Dodge

0.18

 Transparency

0.17

 guides

0.16

Op

0.16

Layer

0.16

 nÃ©t

0.16

 dodge

0.15

 Smart

0.15

 layer

0.15

-opacity

0.15

Activations Density 0.006%

references to digital media and graphic design elements

No Comments

No Known Activations