INDEX

Explanations

references to components and methods in programming, specifically involving a user interface framework

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ios

-0.17

rael

-0.16

ield

-0.15

.scalablytyped

-0.15

ugin

-0.14

ewolf

-0.14

osp

-0.14

.push

-0.14

.insert

-0.14

 Berk

-0.14

POSITIVE LOGITS

btn

0.18

btn

0.17

/documentation

0.15

Luk

0.15

 split

0.15

 label

0.15

_VERTICAL

0.14

txt

0.14

btn

0.14

txt

0.13

Activations Density 0.003%

references to components and methods in programming, specifically involving a user interface framework

No Comments

No Known Activations