INDEX

Explanations

references to components 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ses

-0.16

coming

-0.16

br

-0.16

ustin

-0.15

iferay

-0.15

ings

-0.15

ulta

-0.15

Ð»ÑıÐµÑĤ

-0.15

orie

-0.15

ombok

-0.15

POSITIVE LOGITS

\HttpFoundation

0.20

.DataAnnotations

0.20

ial

0.19

InChildren

0.18

ä»¶

0.18

ized

0.17

so

0.17

ular

0.16

ual

0.16

 migrationBuilder

0.16

Activations Density 0.039%

references to components in a programming context

No Comments

No Known Activations