INDEX

Explanations

references to bibliographic and publication formatting elements

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

à¸±à¸į

-0.16

dom

-0.15

åĤ

-0.15

epad

-0.14

CustomAttributes

-0.14

Ø³Ø§ÙĨ

-0.14

lah

-0.14

IDO

-0.14

ayar

-0.14

phinx

-0.13

POSITIVE LOGITS

 McCl

0.15

iez

0.15

 Landing

0.15

 recep

0.15

liÄį

0.15

les

0.14

 Wolff

0.14

 Ã¢m

0.14

åĲĲ

0.14

olon

0.14

Activations Density 0.029%

references to bibliographic and publication formatting elements

No Comments

No Known Activations