INDEX

Explanations

references to programming concepts and technical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 GObject

-0.15

ãĥ³ãĥĩ

-0.15

 urban

-0.14

blr

-0.14

awe

-0.14

ForObject

-0.14

PostBack

-0.13

">ÃĹ</

-0.13

æĳ©

-0.13

POSITIVE LOGITS

erin

0.16

ZO

0.16

oug

0.15

uela

0.15

çĽĳåĲ¬é¡µéĿ¢

0.15

FC

0.14

tester

0.14

 ÑĤÐ²Ð°

0.14

Æ°á»Ľ

0.14

ress

0.13

Activations Density 0.119%

references to programming concepts and technical terminology

No Comments

No Known Activations