© 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. 129656
    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
    iske
    -0.06
    irs
    -0.05
     /
    -0.05
     p
    -0.05
    oq
    -0.05
    prav
    -0.05
     åį
    -0.05
     solitary
    -0.05
     st
    -0.05
    anca
    -0.05
    POSITIVE LOGITS
    ỹ
    0.07
    ãģŀ
    0.07
    ylko
    0.07
     кÑĸм
    0.07
    imas
    0.07
    apiKey
    0.07
    ëģĶ
    0.07
    wat
    0.07
    nop
    0.07
    оÑħ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.