© 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. 9-LLAMASCOPE-RES-131K
    11. 97477
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in familial contexts

    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
    elah
    -0.07
    ÑĥÑĢÑĥ
    -0.07
    ellers
    -0.07
    iversit
    -0.07
    enet
    -0.07
    alars
    -0.07
    Ñİн
    -0.07
    upy
    -0.07
    celik
    -0.07
    .pretty
    -0.07
    POSITIVE LOGITS
    iac
    0.06
    503
    0.06
    ongs
    0.06
    han
    0.06
    pin
    0.06
    (#)
    0.06
    rap
    0.05
    hor
    0.05
    à¸ģลาà¸ĩ
    0.05
    776
    0.05
    Activations Density 0.005%

    No Known Activations