INDEX

Explanations

references to structured data and component-based frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Sharper

-0.16

rawer

-0.15

alian

-0.15

 Gate

-0.14

unny

-0.14

serde

-0.14

tep

-0.14

rellas

-0.14

illian

-0.14

raham

-0.14

POSITIVE LOGITS

auc

0.15

ØºØ§ÙĨ

0.14

usted

0.14

Ø§ÙĪÛĮ

0.13

Å¾e

0.13

gae

0.13

Ĳ

0.13

onus

0.13

 decrement

0.13

.cert

0.13

Activations Density 0.008%

references to structured data and component-based frameworks

No Comments

No Known Activations