INDEX

Explanations

references to cleaning products and related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

imbus

-0.16

traits

-0.15

Toolkit

-0.15

outil

-0.14

Ø³Ø§ÙĨÛĮ

-0.14

imson

-0.14

arov

-0.14

kip

-0.14

.foundation

-0.14

lemen

-0.13

POSITIVE LOGITS

/Area

0.17

ucken

0.17

apesh

0.15

Ã¡b

0.14

íķŃ

0.14

apur

0.14

utzer

0.13

CanBe

0.13

BarButton

0.13

;display

0.13

Activations Density 0.004%

references to cleaning products and related content

No Comments

No Known Activations