© 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. 2231
    Prev
    Next
    INDEX
    Explanations

    concepts related to marriage and genetic relatedness

    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
    еÑĢин
    -0.09
    hsi
    -0.08
     anale
    -0.08
    subcategory
    -0.07
    linger
    -0.07
    ICODE
    -0.07
    ัà¸įà¸Ĭ
    -0.07
    esthes
    -0.07
    ãĥĨãĤ£
    -0.07
    etration
    -0.07
    POSITIVE LOGITS
     genetic
    0.09
     Genetic
    0.07
     incest
    0.07
    ugen
    0.07
     population
    0.07
     dise
    0.07
     genetics
    0.07
     recess
    0.07
     individuals
    0.07
     autos
    0.06
    Activations Density 0.043%

    No Known Activations