INDEX

Explanations

expressions related to performing actions and activities

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

 Positioned

-0.15

undy

-0.14

ennen

-0.14

RuntimeObject

-0.14

Ð¾ÐºÐ¾Ð»

-0.14

mlin

-0.14

 Franklin

-0.14

])==

-0.14

upe

-0.14

raig

-0.14

POSITIVE LOGITS

 expertise

0.19

 natural

0.19

 passion

0.18

atural

0.17

 Passion

0.17

 favorite

0.17

 Natural

0.17

 familiar

0.17

 favourite

0.17

 strengths

0.17

Activations Density 0.121%

expressions related to performing actions and activities

No Comments

No Known Activations