© 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. 105281
    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
    AYS
    -0.06
    etary
    -0.06
    owski
    -0.06
    urtle
    -0.06
    KeyName
    -0.06
    cmb
    -0.06
    phans
    -0.06
    orsche
    -0.05
    orch
    -0.05
    adian
    -0.05
    POSITIVE LOGITS
    itorio
    0.07
    _exempt
    0.06
    ser
    0.06
    ASY
    0.06
    _loading
    0.06
     anzeigen
    0.06
    ICAST
    0.06
    -hit
    0.06
    ialized
    0.06
    ometr
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.