© 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. 92301
    Prev
    Next
    INDEX
    Explanations

    details about automobile racing history and ownership changes

    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
    uisse
    -0.07
    æĭ³
    -0.07
    аки
    -0.06
    anal
    -0.06
    aki
    -0.06
    hw
    -0.06
     global
    -0.06
    ãģĶãģĸãģĦãģ¾ãģĻ
    -0.06
     worldwide
    -0.06
     гÑĢом
    -0.06
    POSITIVE LOGITS
    _ALIGNMENT
    0.07
    MimeType
    0.06
     tehdy
    0.06
    phet
    0.06
    eprom
    0.06
    _modified
    0.06
    .opens
    0.06
    ariate
    0.06
    imedia
    0.06
    Fetching
    0.06
    Activations Density 0.006%

    No Known Activations