INDEX

Explanations

technical terminology related to electrical engineering and circuit design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

esture

-0.15

%A

-0.15

ptal

-0.14

azel

-0.14

OMX

-0.13

 ÙħØ§Ø¯

-0.13

primir

-0.13

ernal

-0.13

adier

-0.13

ÙĪÙĤ

-0.13

POSITIVE LOGITS

 gate

0.28

gate

0.23

 Gate

0.22

 gates

0.22

Gate

0.21

CM

0.20

DRAM

0.19

 drain

0.19

 Flash

0.19

oxide

0.18

Activations Density 0.010%

technical terminology related to electrical engineering and circuit design

No Comments

No Known Activations