© 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. 2465
    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
    onga
    -0.07
     tslib
    -0.07
    781
    -0.07
    ivated
    -0.06
    annis
    -0.06
     "
    -0.06
    iam
    -0.06
    EMY
    -0.06
    ilis
    -0.06
    HEST
    -0.06
    POSITIVE LOGITS
    _ROM
    0.08
    avou
    0.07
    arts
    0.07
    /*č↵
    0.07
    _Device
    0.07
    vero
    0.06
    iž
    0.06
    .Designer
    0.06
    èıĮ
    0.06
     barr
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.