INDEX

Explanations

technical terms related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

xFD

-0.14

asts

-0.13

auty

-0.12

uve

-0.12

 cigaret

-0.12

ëį°ìĿ´íĬ¸

-0.12

ãİ

-0.12

adox

-0.12

dirty

-0.12

POSITIVE LOGITS

foo

0.42

Foo

0.39

foo

0.38

/foo

0.37

.foo

0.37

Foo

0.36

 some

0.35

(foo

0.34

 hello

0.33

 Some

0.31

Activations Density 0.404%

technical terms related to programming and software development

No Comments

No Known Activations