INDEX

Explanations

references to software components or services within programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Ð¾Ð²Ð¾

-0.15

isque

-0.14

colo

-0.13

»

-0.12

-like

-0.12

erable

-0.12

ÙĪÙħÛĮ

-0.12

 imaginable

-0.12

cra

-0.12

-turned

-0.12

POSITIVE LOGITS

/gtest

0.14

Ð³ÑĢÐ°Ð´

0.13

atre

0.13

OnInit

0.12

bine

0.12

acic

0.12

GIN

0.12

SWG

0.12

tees

0.12

ÑģÐ»Ð¸

0.12

Activations Density 0.063%

references to software components or services within programming contexts

No Comments

No Known Activations