INDEX

Explanations

references to ownership and possession

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Ð¾Ð¼ÐµÑĢ

-0.15

 Viá»ĩc

-0.14

Squ

-0.14

ering

-0.14

-0.13

NG

-0.13

 Narr

-0.13

çļĦæĥħåĨµ

-0.13

 hone

-0.13

ween

-0.13

POSITIVE LOGITS

contents

0.18

 contents

0.17

ilk

0.16

purpose

0.16

esser

0.16

ponents

0.16

ÑĩÐµÐ½

0.15

ody

0.15

eld

0.15

 inception

0.15

Activations Density 0.192%

references to ownership and possession

No Comments

No Known Activations

references to ownership and possession

No Comments

No Known Activations