INDEX

Explanations

code references and line indicators in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ifen

-0.15

amped

-0.15

ongo

-0.15

SES

-0.14

Configurer

-0.14

ãģıãĤĭ

-0.14

 Waterloo

-0.14

 strides

-0.13

 Suspension

-0.13

 Carousel

-0.13

POSITIVE LOGITS

aticon

0.18

_KP

0.16

ÑĩÐ¸Ð¼

0.16

Ð³Ð¸

0.15

 Idea

0.14

elerik

0.14

finity

0.14

@brief

0.14

apolis

0.13

.BorderFactory

0.13

Activations Density 0.005%

code references and line indicators in a programming context

No Comments

No Known Activations