INDEX

Explanations

variations of the sound "oo" in various contexts and forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

itto

-0.16

emoc

-0.16

apor

-0.15

ÑĢÐµÐ¶

-0.15

quez

-0.15

ytt

-0.14

 Äĳá»ĭnh

-0.14

urlencode

-0.14

cljs

-0.14

obus

-0.14

POSITIVE LOGITS

oo

0.27

ool

0.25

ie

0.24

igans

0.22

ery

0.20

chie

0.20

ey

0.20

ies

0.20

ums

0.19

zie

0.19

Activations Density 0.051%

variations of the sound "oo" in various contexts and forms

No Comments

No Known Activations