INDEX

Explanations

references to curry and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Kauf

-0.16

erable

-0.16

.documentation

-0.14

owe

-0.14

ici

-0.14

Joi

-0.14

Ã»t

-0.14

prov

-0.13

Lic

-0.13

Cop

-0.13

POSITIVE LOGITS

arak

0.15

çī©

0.14

POCH

0.14

radu

0.14

ccoli

0.14

á»ģn

0.13

çĺ

0.13

ì£ł

0.13

ALLOC

0.13

MethodInfo

0.13

Activations Density 0.003%

references to curry and its variations

No Comments

No Known Activations