INDEX

Explanations

instances of appreciation and gratitude expressed towards others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

obi

-0.17

arp

-0.15

ixin

-0.15

arkin

-0.14

lus

-0.14

arna

-0.14

OOT

-0.14

Ø±Ø¨

-0.13

.Rad

-0.13

adic

-0.13

POSITIVE LOGITS

ably

0.26

ately

0.19

iable

0.18

iative

0.16

iado

0.16

ble

0.15

ible

0.15

æĹıèĩªæ²»

0.15

INDER

0.15

 Nice

0.14

Activations Density 0.017%

instances of appreciation and gratitude expressed towards others

No Comments

No Known Activations