© 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. 27343
    Prev
    Next
    INDEX
    Explanations

    elements related to familial relationships and genetic inheritance

    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
    aea
    -0.08
    ninger
    -0.08
    ween
    -0.07
    ;element
    -0.07
    vides
    -0.07
    лем
    -0.07
    æĻ¨
    -0.07
    елов
    -0.07
    deo
    -0.07
    ideo
    -0.07
    POSITIVE LOGITS
     generations
    0.09
     inheritance
    0.08
     passed
    0.08
     inherit
    0.08
     transmission
    0.07
     repro
    0.07
     sons
    0.07
     generation
    0.07
    sons
    0.07
     inherited
    0.07
    Activations Density 0.004%

    No Known Activations