INDEX

Explanations

technical terminology and concepts related to neural networks and protein functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

pill

-0.15

_icall

-0.15

(æ°´

-0.15

"profile

-0.14

FTA

-0.14

_lng

-0.14

 libertin

-0.14

èŃľ

-0.14

ÏĢÎµÎ¹

-0.14

 ÎºÎ¿Ïģ

-0.14

POSITIVE LOGITS

 layer

0.35

 Layer

0.32

Layer

0.31

layer

0.31

 layers

0.30

-layer

0.30

 weights

0.29

 weight

0.29

 neurons

0.28

 Layers

0.28

Activations Density 0.019%

technical terminology and concepts related to neural networks and protein functions

No Comments

No Known Activations