© 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. 17-LLAMASCOPE-RES-131K
    11. 94360
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    vin
    -0.06
    å¹ħ
    -0.06
    âĢİ
    -0.06
    Occurred
    -0.06
    cestor
    -0.06
    оваÑĢ
    -0.06
     ajud
    -0.06
    âĦĸ
    -0.06
     Ston
    -0.05
    Reporter
    -0.05
    POSITIVE LOGITS
     circulation
    0.07
    chy
    0.07
    comings
    0.07
    /copyleft
    0.07
    inho
    0.07
    achines
    0.07
    æ°ı
    0.07
    anten
    0.06
    uttle
    0.06
    ül
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.