© 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 EvalsExportsinterp-engineNEWAPI 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. 104710
    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
    ÑĢÑĥн
    -0.07
    ASK
    -0.07
    ượu
    -0.07
    ABCDEFG
    -0.06
    AREST
    -0.06
    çħ§
    -0.06
    xis
    -0.06
    zer
    -0.06
    amientos
    -0.06
    åIJ¾
    -0.06
    POSITIVE LOGITS
    lev
    0.07
    954
    0.06
    iosa
    0.06
    aley
    0.06
     bore
    0.06
    iolet
    0.06
    875
    0.06
    orce
    0.06
    inform
    0.06
     FileAccess
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.