INDEX

Explanations

references to product and shopping promotions

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

unes

-0.16

omencl

-0.15

 Keller

-0.15

ware

-0.15

&amp

-0.14

 perennial

-0.14

 Stick

-0.14

icens

-0.14

ouro

-0.14

ro

-0.14

POSITIVE LOGITS

âĸ²

0.17

EPROM

0.16

avis

0.16

ãĥ³ãĥĦ

0.15

iazza

0.15

iker

0.14

uddy

0.14

_migration

0.14

ÂłÐ³

0.14

.jboss

0.14

Activations Density 0.044%

references to product and shopping promotions

No Comments

No Known Activations