INDEX

Explanations

occurrences of the word "Bro" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ulas

-0.18

alse

-0.17

rum

-0.16

ras

-0.16

rÃ³

-0.15

rose

-0.15

pent

-0.15

ted

-0.15

POSITIVE LOGITS

oklyn

0.29

ccoli

0.26

oding

0.24

chure

0.23

okes

0.23

cade

0.22

oks

0.20

bro

0.20

iler

0.20

swer

0.19

Activations Density 0.008%

occurrences of the word "Bro" and its variations

No Comments

No Known Activations