INDEX

Explanations

elements related to audio processing and speech recognition technology

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

allon

-0.20

ÐµÑī

-0.15

vul

-0.15

ificio

-0.14

ulin

-0.14

LOPT

-0.14

ÐķÐ¢

-0.14

ottes

-0.13

POSITIVE LOGITS

 speech

0.37

 Speech

0.32

Speech

0.31

speech

0.30

 pitch

0.25

 speaker

0.25

 Speaker

0.24

peech

0.24

cep

0.23

Speaker

0.23

Activations Density 0.023%

elements related to audio processing and speech recognition technology

No Comments

No Known Activations