INDEX

Explanations

keywords and parameters related to programming functions and their operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

odore

-0.33

atomy

-0.25

atre

-0.25

adays

-0.24

etheless

-0.19

tlement

-0.19

anmar

-0.19

xiety

-0.17

ou

-0.16

gether

-0.15

POSITIVE LOGITS

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

0.22

plevel

0.17

ÐĲÑĢÑħÑĸÐ²Ð¾Ð²Ð°Ð½Ð¾

0.17

isan

0.16

 latter

0.16

efined

0.15

Ãºb

0.14

.à¸¨

0.14

ocommerce

0.14

chedulers

0.14

Activations Density 0.763%

keywords and parameters related to programming functions and their operations

No Comments

No Known Activations