INDEX

Explanations

instances of the word "take" and variations of it in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 alike

-0.15

æĳĺ

-0.15

 samot

-0.15

rem

-0.14

VEN

-0.14

preview

-0.14

 taste

-0.13

dig

-0.13

 previews

-0.13

alta

-0.13

POSITIVE LOGITS

loff

0.19

itur

0.18

alet

0.15

uran

0.14

Î¼ÏĢÎ¿

0.14

lisi

0.14

itchens

0.14

/*č↵

0.14

 gá»Ĺ

0.14

eturn

0.14

Activations Density 0.087%

instances of the word "take" and variations of it in different contexts

No Comments

No Known Activations