INDEX

Explanations

programming-related terms and class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

vfs

-0.15

_cate

-0.14

 Jude

-0.14

bourg

-0.14

iris

-0.14

 convenient

-0.14

itesse

-0.14

ÎµÎ¹

-0.14

ependency

-0.13

 speeds

-0.13

POSITIVE LOGITS

 shipping

0.19

 sandbox

0.19

Shipping

0.18

 Buyer

0.18

 buyer

0.18

 Sandbox

0.18

amount

0.18

buyer

0.18

.sale

0.18

 Shipping

0.18

Activations Density 0.009%

programming-related terms and class definitions

No Comments

No Known Activations