© 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. 3574
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to sexual preferences and fetishes

    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
    tha
    -0.07
     prostit
    -0.06
    è«
    -0.06
    ãĤ«ãĥ¼
    -0.06
     Beer
    -0.06
     datings
    -0.06
    çİĩ
    -0.06
     brides
    -0.06
     raped
    -0.06
    apiro
    -0.06
    POSITIVE LOGITS
     bondage
    0.07
     fantasies
    0.07
     dungeon
    0.07
    fet
    0.07
    utas
    0.07
     domina
    0.07
     Fet
    0.07
    /releases
    0.07
     fantasy
    0.07
     domin
    0.07
    Activations Density 0.083%

    No Known Activations