INDEX

Explanations

references to new developments and personal opinions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ttp

-0.15

kud

-0.15

Ð»ÐºÐ¸

-0.15

decess

-0.14

onta

-0.14

iteli

-0.14

Ð»ÑıÐ´

-0.14

uby

-0.14

lette

-0.13

ilder

-0.13

POSITIVE LOGITS

abor

0.14

 GOODS

0.14

bsites

0.13

HING

0.13

--)

0.13

DSL

0.13

atre

0.13

.LookAndFeel

0.13

SSERT

0.13

 Prometheus

0.12

Activations Density 1.842%

references to new developments and personal opinions

No Comments

No Known Activations