© 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. 117579
    Prev
    Next
    INDEX
    Explanations

    phrases 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
    unde
    -0.06
     Harding
    -0.06
     handy
    -0.06
    ÅĻej
    -0.06
    ivent
    -0.06
     invol
    -0.06
    缤
    -0.06
    uitka
    -0.06
    igy
    -0.06
    ega
    -0.05
    POSITIVE LOGITS
     subsequent
    0.09
    æİ¥çĿĢ
    0.07
     tattoo
    0.07
    ÑĮ
    0.06
    arnation
    0.06
    reveal
    0.06
     subsequently
    0.06
    å´
    0.06
    .chart
    0.06
    BOUND
    0.06
    Activations Density 0.017%

    No Known Activations