© 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 EvalsExportsAPI 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. 76468
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to liability and compensation

    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
    ipur
    -0.06
    idal
    -0.06
    ews
    -0.06
    atable
    -0.06
    olio
    -0.06
    wner
    -0.06
    oyo
    -0.06
    ackets
    -0.06
    udi
    -0.06
    ypse
    -0.06
    POSITIVE LOGITS
     Burr
    0.07
    ÄĽti
    0.07
    URI
    0.07
    uri
    0.07
    .LookAndFeel
    0.07
    inar
    0.06
    urus
    0.06
    inue
    0.06
    tery
    0.06
    onis
    0.06
    Activations Density 0.001%

    No Known Activations