© 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. 88433
    Prev
    Next
    INDEX
    Explanations

    terms related to skincare and its effects on health

    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
    еÑĢо
    -0.07
    ENO
    -0.07
    vice
    -0.06
    adm
    -0.06
    lor
    -0.06
    ume
    -0.06
     suche
    -0.06
     trp
    -0.06
    unic
    -0.06
    .arc
    -0.06
    POSITIVE LOGITS
     your
    0.09
     cells
    0.07
     unders
    0.07
    usty
    0.07
    swick
    0.06
    your
    0.06
    ãĥ¼ãĥª
    0.06
     extrem
    0.06
    -qu
    0.06
    iele
    0.06
    Activations Density 0.009%

    No Known Activations