© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125875
    Prev
    Next
    INDEX
    Explanations

    concepts related to property rights and government regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uai
    -0.07
    idine
    -0.07
     Saud
    -0.06
    loquent
    -0.06
    Į
    -0.06
     sana
    -0.06
    еви
    -0.06
     Haut
    -0.06
    @mail
    -0.06
    747
    -0.06
    POSITIVE LOGITS
     property
    0.12
     Property
    0.11
    property
    0.10
    Property
    0.09
    -property
    0.09
     PROPERTY
    0.08
    _Property
    0.07
     tak
    0.07
    .property
    0.07
    stown
    0.07
    Activations Density 0.007%

    No Known Activations