INDEX

Explanations

variations of the word "tie" related to connections or unions

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

 voks

-0.18

ync

-0.16

lah

-0.15

imers

-0.15

wards

-0.14

ÑĬÐµÐ¼

-0.14

sti

-0.14

etics

-0.14

st

-0.14

ipple

-0.13

POSITIVE LOGITS

 knot

0.30

 Knot

0.28

 knots

0.27

breaker

0.25

 tying

0.24

tie

0.23

tie

0.22

 tied

0.21

 ties

0.20

breaking

0.19

Activations Density 0.017%

variations of the word "tie" related to connections or unions

No Comments

No Known Activations