© 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. 94705
    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
    lock
    -0.07
    ions
    -0.07
    大åħ¨
    -0.06
    ique
    -0.06
    ver
    -0.06
    392
    -0.06
    าà¸Īารย
    -0.06
     ä»Ĭ
    -0.06
    ãģ®ãģĬ
    -0.06
    LOCKS
    -0.06
    POSITIVE LOGITS
    ibri
    0.07
    anela
    0.07
     Flesh
    0.06
    elage
    0.06
    emme
    0.06
    enas
    0.06
    edula
    0.06
    omor
    0.06
    adÃŃ
    0.06
     Tw
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.