© 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. 15-LLAMASCOPE-RES-131K
    11. 87132
    Prev
    Next
    INDEX
    Explanations

    elements related to game mechanics and player guidance

    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
    bett
    -0.06
    меÑĩ
    -0.06
     wij
    -0.06
    _feedback
    -0.06
     form
    -0.06
    oje
    -0.06
    ada
    -0.06
     дела
    -0.06
    à¸ķา
    -0.06
     Dice
    -0.06
    POSITIVE LOGITS
    ufen
    0.08
    zig
    0.08
    lech
    0.07
    odos
    0.07
    aze
    0.07
    :NSLocalizedString
    0.07
    âķIJâķIJ
    0.07
    à¥įसर
    0.07
    ãĥ³ãĥĪ
    0.07
    pez
    0.06
    Activations Density 0.007%

    No Known Activations