© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88861
    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
    _COMPAT
    -0.07
    .ro
    -0.06
     Vak
    -0.06
     complain
    -0.06
     ÅŁik
    -0.06
     Cyril
    -0.06
    âĹİ
    -0.06
    wk
    -0.06
    stown
    -0.06
    hed
    -0.06
    POSITIVE LOGITS
    InMillis
    0.06
    DataSource
    0.06
    dbg
    0.06
    lingen
    0.06
    OfSize
    0.06
    noop
    0.06
    NullException
    0.06
    رÙĬÙģ
    0.06
    OfMonth
    0.06
    ovenant
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.