INDEX

Explanations

words and concepts related to literacy and reading development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

arih

-0.16

idak

-0.16

çĦ¡ãģĹ

-0.15

InChildren

-0.15

çµ

-0.14

 addCriterion

-0.14

guards

-0.14

Î³ÎºÎ¿

-0.14

nton

-0.14

ooke

-0.14

POSITIVE LOGITS

 pros

0.17

 experts

0.17

 multit

0.17

ìļ©

0.16

izia

0.16

cole

0.15

Digits

0.15

 Expert

0.15

rej

0.15

><![

0.15

Activations Density 0.237%

words and concepts related to literacy and reading development

No Comments

No Known Activations