INDEX

Explanations

occurrences of the term "French" and relevant numerical relationships to it

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

jit

-0.16

adem

-0.16

.Abstractions

-0.15

ÙĬØ±Ø§

-0.14

 nors

-0.14

greg

-0.14

stav

-0.14

ÑģÑĤÑĢÐ¾Ð²

-0.14

ÅĻe

-0.14

ity

-0.14

POSITIVE LOGITS

man

0.28

men

0.28

boro

0.24

ified

0.23

-speaking

0.22

 Quarter

0.22

 fries

0.21

spe

0.21

mans

0.20

 bulld

0.20

Activations Density 0.022%

occurrences of the term "French" and relevant numerical relationships to it

No Comments

No Known Activations