© 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. 78976
    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
     leider
    -0.07
    íķĢ
    -0.07
    ADDE
    -0.07
    /cpp
    -0.07
    enga
    -0.06
    .synthetic
    -0.06
     Sadly
    -0.06
     deepen
    -0.06
    marsh
    -0.06
     ÄĮes
    -0.06
    POSITIVE LOGITS
    imus
    0.07
    EIF
    0.07
    ulas
    0.06
    inh
    0.06
     eas
    0.06
    idable
    0.06
    esterday
    0.06
    座
    0.06
    èĢ
    0.06
    immel
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.