INDEX

Explanations

instances of the expression "Ha" in various contexts

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

lec

-0.16

Aur

-0.15

fant

-0.14

horn

-0.14

aur

-0.14

pong

-0.14

hide

-0.14

Ã¡vÄĽ

-0.14

timeout

-0.14

jets

-0.14

POSITIVE LOGITS

unted

0.24

iku

0.23

ha

0.23

Ha

0.21

ifax

0.20

Ha

0.20

unting

0.20

iley

0.20

ifa

0.19

emat

0.19

Activations Density 0.010%

instances of the expression "Ha" in various contexts

No Comments

No Known Activations