INDEX

Explanations

AWS resource identifiers in the context of permissions and policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

cao

-0.14

 bÃłi

-0.14

portun

-0.14

á»Ĳ

-0.14

erguson

-0.14

dio

-0.14

addtogroup

-0.13

ä¸»ä»»

-0.13

ìľ

-0.13

frag

-0.13

POSITIVE LOGITS

askan

0.17

inka

0.17

Locker

0.15

åĬ©

0.15

 Amazon

0.15

 pulumi

0.14

 sworn

0.14

 charge

0.14

£

0.14

 pilot

0.14

Activations Density 0.031%

AWS resource identifiers in the context of permissions and policies

No Comments

No Known Activations