INDEX

Explanations

technical terms related to programming and data processing

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

adox

-0.16

 -*-č↵

-0.14

BaseContext

-0.14

ieces

-0.13

auty

-0.13

phan

-0.13

unei

-0.12

 ëħĦëıĦë³Ħ

-0.12

 handjob

-0.12

pill

-0.12

POSITIVE LOGITS

foo

0.36

 some

0.34

.foo

0.34

foo

0.33

Foo

0.33

/foo

0.32

Foo

0.32

 Some

0.30

 hello

0.30

fo

0.28

Activations Density 0.578%

technical terms related to programming and data processing

No Comments

No Known Activations