INDEX

Explanations

references to award winners and competitive achievements in educational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÃŃc

-0.18

anzi

-0.17

jang

-0.15

 counted

-0.14

gaard

-0.14

auc

-0.14

.platform

-0.14

ÑĨÑĮÐºÐ¸Ð¹

-0.14

 newArr

-0.14

 piger

-0.14

POSITIVE LOGITS

indh

0.14

 sele

0.14

 selection

0.14

 ripple

0.14

IDL

0.14

ties

0.14

nt

0.13

å¦Ĥä¸ĭ

0.13

tie

0.13

Wer

0.13

Activations Density 0.056%

references to award winners and competitive achievements in educational contexts

No Comments

No Known Activations