© 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. 126693
    Prev
    Next
    INDEX
    Explanations

    references to homosexuality and its moral implications

    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
    iverz
    -0.08
    ofilm
    -0.07
    StateException
    -0.07
    endid
    -0.07
    outu
    -0.07
     Porn
    -0.07
    abyrinth
    -0.07
     %+
    -0.07
    uiltin
    -0.07
    olland
    -0.07
    POSITIVE LOGITS
     pair
    0.07
     anal
    0.07
     sod
    0.07
    unn
    0.07
     consenting
    0.07
    /preferences
    0.07
     Orient
    0.06
     consent
    0.06
     bis
    0.06
     practiced
    0.06
    Activations Density 0.010%

    No Known Activations