INDEX

Explanations

programming-related terms and code structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

UDO

-0.16

hi

-0.14

PMC

-0.14

 Accordingly

-0.14

csi

-0.13

BUF

-0.13

elsen

-0.13

oten

-0.13

 classname

-0.13

Classes

-0.13

POSITIVE LOGITS

.exports

0.31

.export

0.18

 hunt

0.18

icz

0.17

ulia

0.17

Ã¹i

0.16

eous

0.16

 Validates

0.16

 Hammer

0.15

 fitte

0.15

Activations Density 0.014%

programming-related terms and code structures

No Comments

No Known Activations