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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 105016
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts involving the concept of familial relationships and living arrangements

    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
    queda
    -0.08
    amac
    -0.07
    egade
    -0.07
    ucz
    -0.07
    anager
    -0.07
    stras
    -0.07
    eka
    -0.07
    kea
    -0.07
    rift
    -0.07
    ritz
    -0.06
    POSITIVE LOGITS
     families
    0.07
    annya
    0.07
    ONTAL
    0.07
    /contact
    0.06
    IFA
    0.06
    ado
    0.06
    208
    0.06
     Cir
    0.06
    ough
    0.06
    ãĥªãĥ³ãĤ¯
    0.06
    Activations Density 0.011%

    No Known Activations