© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89121
    Prev
    Next
    INDEX
    Explanations

    terms related to skincare and maintenance

    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
    ìĤ¬ìĿ´
    -0.07
    ToDelete
    -0.07
    ubat
    -0.06
     GOODMAN
    -0.06
     weights
    -0.06
    clr
    -0.06
     -*
    -0.06
     èĩ
    -0.06
     cleaned
    -0.06
    ToRemove
    -0.06
    POSITIVE LOGITS
     Skin
    0.09
     skin
    0.08
     moistur
    0.08
     dry
    0.07
     hydr
    0.07
    akh
    0.07
    akis
    0.07
     Dry
    0.07
    mo
    0.07
     moisture
    0.07
    Activations Density 0.029%

    No Known Activations