INDEX

Explanations

variations of the letter 'k' in different contexts

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

-0.15

lew

-0.15

uko

-0.14

itter

-0.14

Club

-0.14

 breve

-0.14

(:,:,

-0.14

 NumberOf

-0.13

mpeg

-0.13

POSITIVE LOGITS

bles

0.17

ross

0.15

asca

0.15

ãģ¹

0.14

esz

0.14

cona

0.14

 Competitive

0.14

 competitive

0.14

ìħ

0.14

corn

0.14

Activations Density 0.003%

variations of the letter 'k' in different contexts

No Comments

No Known Activations