INDEX

Explanations

instances of the word "Rose" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

resse

-0.19

-0.17

errer

-0.16

arget

-0.16

RESS

-0.15

è¶£

-0.15

thest

-0.15

FontAwesome

-0.14

FileChooser

-0.14

usi

-0.14

POSITIVE LOGITS

mary

0.47

bud

0.34

MARY

0.30

anne

0.26

maries

0.26

velt

0.25

hip

0.25

bery

0.24

/ros

0.23

anna

0.22

Activations Density 0.009%

instances of the word "Rose" and related variations

No Comments

No Known Activations