© 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. 17471
    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
    åĬŁ
    -0.06
    emi
    -0.06
    خر
    -0.06
    öl
    -0.06
    'gc
    -0.06
     defaultCenter
    -0.06
    .Sdk
    -0.06
     PureComponent
    -0.06
     Foreign
    -0.06
    NSNotification
    -0.06
    POSITIVE LOGITS
    ioni
    0.07
    arts
    0.07
    artz
    0.07
    ubat
    0.07
    quet
    0.07
    aje
    0.07
    uke
    0.06
    iten
    0.06
     Sanctuary
    0.06
    ks
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.