© 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. 39390
    Prev
    Next
    INDEX
    Explanations

    terms related to patents and intellectual property

    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
    uien
    -0.07
    orest
    -0.07
    ivery
    -0.07
    _menus
    -0.07
     routine
    -0.07
    ิà¸į
    -0.06
    аннÑĭ
    -0.06
    iver
    -0.06
    owie
    -0.06
    (cf
    -0.06
    POSITIVE LOGITS
    ahan
    0.06
    istung
    0.06
     Stud
    0.06
    ridor
    0.06
     Dickinson
    0.06
    antha
    0.06
    assi
    0.06
     Robertson
    0.06
    atan
    0.06
    osi
    0.06
    Activations Density 0.011%

    No Known Activations