INDEX

Explanations

elements related to division and portions in 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 @ 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

 derec

-0.15

oron

-0.15

ppv

-0.15

 nearby

-0.14

eÅŁ

-0.14

 kanal

-0.14

semb

-0.14

jdk

-0.13

åĲĪæł¼

-0.13

bon

-0.13

POSITIVE LOGITS

 portion

0.51

 part

0.45

 portions

0.43

 parte

0.39

éĥ¨åĪĨ

0.39

 section

0.38

 halves

0.36

portion

0.36

 parts

0.36

 Part

0.36

Activations Density 0.289%

elements related to division and portions in various contexts

No Comments

No Known Activations