© 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. 17475
    Prev
    Next
    INDEX
    Explanations

    references to guardianship and protective figures

    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
    èŃľ
    -0.07
    иÑģÑģ
    -0.07
    rette
    -0.07
    redients
    -0.07
    .getExternal
    -0.06
    deen
    -0.06
    ipes
    -0.06
    getExtension
    -0.06
    iese
    -0.06
    оÑĦ
    -0.06
    POSITIVE LOGITS
     patron
    0.08
    ossed
    0.06
    loys
    0.06
    çªģ
    0.06
    -oper
    0.06
     Patron
    0.06
     patrons
    0.06
     Duke
    0.06
    /helpers
    0.06
    ë
    0.06
    Activations Density 0.002%

    No Known Activations