INDEX

Explanations

references to specific areas of research or focus

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

arus

-0.17

xico

-0.15

HH

-0.15

uur

-0.15

 SÆ¡n

-0.14

Multiplicity

-0.14

arde

-0.14

ilst

-0.14

POSITIVE LOGITS

 field

0.31

 areas

0.29

 fields

0.28

 area

0.28

 Bereich

0.27

 lÄ©nh

0.26

 Ã¡rea

0.25

areas

0.25

 category

0.25

-field

0.25

Activations Density 0.145%

references to specific areas of research or focus

No Comments

No Known Activations