INDEX

Explanations

terms related to processes, systems, and functionality within various contexts

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

 cerco

-0.15

adÃŃ

-0.15

Ð»ÑıÐ½

-0.14

Mik

-0.14

afa

-0.14

ModelIndex

-0.13

åĽ²

-0.13

adi

-0.13

nis

-0.13

 sticking

-0.13

POSITIVE LOGITS

 exists

0.32

 exist

0.32

 Exists

0.26

 Exist

0.26

 existence

0.25

exist

0.25

Exist

0.25

 existed

0.24

åŃĺåľ¨

0.23

exists

0.23

Activations Density 0.274%

terms related to processes, systems, and functionality within various contexts

No Comments

No Known Activations