© 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. 59440
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and operations related to vector analysis and transformations

    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
     miêu
    -0.06
     ///<
    -0.06
    à¥Ģà¤Ł
    -0.06
    SWG
    -0.06
    ///<
    -0.06
    atrix
    -0.05
    .goto
    -0.05
     Frank
    -0.05
    -gnu
    -0.05
     sched
    -0.05
    POSITIVE LOGITS
     thereof
    0.11
     of
    0.10
     của
    0.08
    OfFile
    0.07
    :animated
    0.07
    /Gate
    0.07
    æij
    0.07
    imas
    0.07
    aton
    0.07
    #Region
    0.07
    Activations Density 0.147%

    No Known Activations