INDEX

Explanations

references to the lotus flower

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

het

-0.18

holes

-0.17

hole

-0.16

utters

-0.15

 optics

-0.15

ialis

-0.15

icides

-0.15

alia

-0.15

abad

-0.15

-0.14

POSITIVE LOGITS

tery

0.28

ting

0.25

ter

0.22

issement

0.21

.lot

0.21

TER

0.21

nict

0.20

lot

0.19

ofire

0.19

tering

0.18

Activations Density 0.018%

references to the lotus flower

No Comments

No Known Activations