INDEX

Explanations

references to AWS resource policies and roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

adian

-0.16

lien

-0.15

ium

-0.14

vale

-0.14

afen

-0.14

Rx

-0.14

tons

-0.14

 Leer

-0.13

iple

-0.13

vla

-0.13

POSITIVE LOGITS

igi

0.15

uffs

0.14

 Mund

0.14

hits

0.14

 Alto

0.14

aversable

0.14

ervo

0.14

ajor

0.13

hip

0.13

 Stub

0.13

Activations Density 0.178%

references to AWS resource policies and roles

No Comments

No Known Activations