INDEX

Explanations

references to children and family-oriented activities or accommodations

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

ondon

-0.18

ephy

-0.17

icode

-0.16

oron

-0.15

à¤łà¤¨

-0.14

ince

-0.14

ÑĥÐ»ÑıÑĢ

-0.14

	define

-0.14

oul

-0.14

 Gest

-0.14

POSITIVE LOGITS

 Children

0.18

 portion

0.17

Children

0.17

 children

0.16

InSection

0.15

 portions

0.15

kes

0.15

 section

0.15

Kid

0.15

 Safety

0.14

Activations Density 0.072%

references to children and family-oriented activities or accommodations

No Comments

No Known Activations