INDEX

Explanations

references to the variety and differences in languages and dialects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 translation

-0.16

\:

-0.14

 translations

-0.14

eprom

-0.14

Pru

-0.14

indr

-0.14

à¤¸à¤°

-0.14

cap

-0.14

ady

-0.14

 translated

-0.14

POSITIVE LOGITS

 dialect

0.29

dia

0.28

dia

0.26

 dial

0.24

 register

0.23

 registers

0.23

 varieties

0.23

registers

0.22

 Variety

0.22

Standard

0.21

Activations Density 0.025%

references to the variety and differences in languages and dialects

No Comments

No Known Activations