INDEX

Explanations

references to user characteristics or reviews related to products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

hci

-0.17

ask

-0.16

icip

-0.16

Äįi

-0.15

wert

-0.15

uan

-0.14

okol

-0.14

seau

-0.14

lei

-0.14

ServiceProvider

-0.14

POSITIVE LOGITS

 particular

0.16

allon

0.16

his

0.14

èĿ

0.14

 Russ

0.14

orb

0.14

rupa

0.14

 unmist

0.13

Ð²Ð¸Ð´

0.13

auge

0.13

Activations Density 0.045%

references to user characteristics or reviews related to products or services

No Comments

No Known Activations