INDEX

Explanations

phrases and words that describe inadequacies or deficiencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 subsidi

-0.15

 Heavenly

-0.14

qing

-0.14

 Autodesk

-0.14

 conc

-0.14

onest

-0.14

GNUC

-0.13

nr

-0.13

erin

-0.13

andon

-0.13

POSITIVE LOGITS

ainen

0.17

Ø§Ø¡

0.17

okit

0.17

FAULT

0.15

 Walls

0.15

ä¿ºãģ¯

0.15

íĺľ

0.14

alis

0.14

æ¸

0.14

.www

0.14

Activations Density 0.167%

phrases and words that describe inadequacies or deficiencies

No Comments

No Known Activations