INDEX

Explanations

terms related to UI components, specifically those that involve collapsible elements and layout structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ondo

-0.15

gly

-0.15

æ²

-0.15

EGA

-0.14

diag

-0.14

uales

-0.14

chaft

-0.14

thood

-0.14

ongo

-0.14

POSITIVE LOGITS

owell

0.15

corp

0.15

acker

0.15

RD

0.15

prav

0.14

arella

0.14

 Ð¼Ð¾ÑĤ

0.14

ÄŁit

0.14

acco

0.14

Fn

0.14

Activations Density 0.008%

terms related to UI components, specifically those that involve collapsible elements and layout structures

No Comments

No Known Activations