© 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. 74031
    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
    .scalablytyped
    -0.09
    blick
    -0.08
    readcr
    -0.07
    zon
    -0.07
    ailer
    -0.07
    Ìģt
    -0.07
     luder
    -0.07
    sında
    -0.06
    edla
    -0.06
    ichtig
    -0.06
    POSITIVE LOGITS
    ddy
    0.06
    imedia
    0.06
     Gio
    0.06
    oli
    0.06
     shell
    0.06
     Inst
    0.06
     Dist
    0.06
     inst
    0.06
    alker
    0.06
    थ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.