© 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. 9-LLAMASCOPE-RES-131K
    11. 95224
    Prev
    Next
    INDEX
    Explanations

    references to spa and wellness facilities, particularly saunas and steam rooms

    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
    pent
    -0.07
    对æĸ¹
    -0.07
    çĩĥ
    -0.07
    e
    -0.06
    uben
    -0.06
    UEL
    -0.06
     offices
    -0.06
     gou
    -0.06
    zig
    -0.06
    à¹ĭ
    -0.06
    POSITIVE LOGITS
     Skin
    0.08
    ære
    0.07
     skin
    0.07
    adir
    0.07
    .Skin
    0.07
    skin
    0.06
    /stream
    0.06
    rosse
    0.06
     sess
    0.06
    nid
    0.06
    Activations Density 0.002%

    No Known Activations