INDEX

Explanations

terms related to procedures and actions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

lob

-0.19

Ð¼Ñı

-0.17

Applied

-0.16

pper

-0.15

ges

-0.14

 Serving

-0.14

avern

-0.14

erland

-0.14

 Applied

-0.14

 espect

-0.14

POSITIVE LOGITS

 ÏĢÏģÎ¿ÏĤ

0.21

 ready

0.20

 undergoing

0.17

åĩºåİ»

0.17

for

0.16

 scheduling

0.16

amodel

0.15

.ActionListener

0.15

ä¾Ľ

0.15

 undergo

0.15

Activations Density 0.172%

terms related to procedures and actions in various contexts

No Comments

No Known Activations