© 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. 29405
    Prev
    Next
    INDEX
    Explanations

    names and titles of authoritative figures, particularly in a political or royal context

    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
    erton
    -0.06
     rocket
    -0.06
    hausen
    -0.06
    ouve
    -0.06
     uniform
    -0.06
    edia
    -0.05
    noch
    -0.05
    ä¸Ģç§į
    -0.05
    EDIA
    -0.05
     sel
    -0.05
    POSITIVE LOGITS
    ierge
    0.07
    ç¨
    0.07
     imz
    0.07
    sled
    0.07
    _Real
    0.07
    кÑĢаÑĹ
    0.06
    کت
    0.06
    #ad
    0.06
    REA
    0.06
    aniem
    0.06
    Activations Density 0.030%

    No Known Activations