© 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. 107380
    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
    -------------</
    -0.07
     cân
    -0.07
    awi
    -0.07
    #
    -0.07
    ----------</
    -0.06
    ิà¹ī
    -0.06
    eldom
    -0.06
    éĺħ读次æķ°
    -0.06
    arhus
    -0.06
    >window
    -0.06
    POSITIVE LOGITS
    umen
    0.07
     maybe
    0.07
    ENE
    0.07
     zwar
    0.07
    ummy
    0.06
     vyp
    0.06
    odon
    0.06
     rop
    0.06
     fuck
    0.06
     fucked
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.