INDEX

Explanations

terms related to widgets and templates in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ãģ¾ãģŁ

-0.20

aug

-0.20

.Automation

-0.18

erot

-0.17

eration

-0.17

aÃ§

-0.16

orie

-0.16

erable

-0.16

silver

-0.16

coming

-0.16

POSITIVE LOGITS

ry

0.21

ified

0.20

ized

0.20

lot

0.19

ly

0.17

son

0.16

ä»¬

0.16

shine

0.16

 ÑģÐ¾Ð±Ð¾Ð¹

0.16

Activations Density 0.341%

terms related to widgets and templates in a technical context

No Comments

No Known Activations