INDEX

Explanations

mentions of the term "cab."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

åłĤ

-0.21

isans

-0.17

itarian

-0.16

 Hint

-0.15

elps

-0.15

ilor

-0.15

zet

-0.15

yk

-0.15

_SO

-0.14

Ð¾Ð»Ñİ

-0.14

POSITIVE LOGITS

aret

0.30

oose

0.29

ernet

0.28

ildo

0.26

rio

0.24

ecera

0.24

Cab

0.23

Cab

0.22

cab

0.21

oodle

0.19

Activations Density 0.008%

mentions of the term "cab."

No Comments

No Known Activations