© 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. 14756
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements of ingredients in recipes

    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
    864
    -0.07
     partida
    -0.07
    lico
    -0.07
    peon
    -0.06
    REA
    -0.06
    rana
    -0.06
    zdy
    -0.06
    edy
    -0.06
    ENDED
    -0.06
    ãģįãģª
    -0.06
    POSITIVE LOGITS
    alink
    0.07
    κÏĮ
    0.06
     Yosh
    0.06
    chai
    0.06
    ocracy
    0.06
    mail
    0.06
    VAS
    0.06
    _apps
    0.06
     Creatures
    0.06
     Unblock
    0.05
    Activations Density 0.040%

    No Known Activations