© 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. 54920
    Prev
    Next
    INDEX
    Explanations

    references to sexuality and sexual themes

    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
    elson
    -0.07
    tha
    -0.06
    ĨĴ
    -0.06
    160
    -0.06
    ine
    -0.06
    gae
    -0.06
     Bud
    -0.06
    erken
    -0.06
    eÅŁ
    -0.06
     Funk
    -0.06
    POSITIVE LOGITS
     Dom
    0.07
     Schwarz
    0.07
     BDSM
    0.07
    зм
    0.07
     bondage
    0.07
    _INITIALIZER
    0.07
    Clr
    0.07
    pdb
    0.06
    Volt
    0.06
    ialog
    0.06
    Activations Density 0.004%

    No Known Activations