© 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. 72328
    Prev
    Next
    INDEX
    Explanations

    terms related to dental and aesthetic procedures

    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
    ï¿£
    -0.07
    elib
    -0.07
    Agency
    -0.07
    伸
    -0.07
     toes
    -0.07
    bubble
    -0.07
    stretch
    -0.07
    êu
    -0.07
    avery
    -0.07
    _VAR
    -0.07
    POSITIVE LOGITS
     contour
    0.09
     contours
    0.07
     facial
    0.07
     fac
    0.07
     sculpt
    0.07
     natural
    0.07
     expression
    0.07
    hes
    0.06
     Sculpt
    0.06
    eger
    0.06
    Activations Density 0.003%

    No Known Activations