© 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. 57683
    Prev
    Next
    INDEX
    Explanations

    elements related to invitations, especially wedding invitations

    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
    IODevice
    -0.09
    ế
    -0.08
    Ñģок
    -0.08
    radan
    -0.08
    .Networking
    -0.08
    ùng
    -0.08
    .unlock
    -0.08
     excer
    -0.08
     Retorna
    -0.08
    getSingleton
    -0.08
    POSITIVE LOGITS
    0.07
    ,
    0.07
     ,
    0.06
     all
    0.06
     /
    0.06
     Freed
    0.06
     Pick
    0.06
     pick
    0.06
     cost
    0.06
     J
    0.05
    Activations Density 0.034%

    No Known Activations