© 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. 17-LLAMASCOPE-RES-131K
    11. 87432
    Prev
    Next
    INDEX
    Explanations

    references to urban and natural environments and their integration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    pio
    -0.07
    Fld
    -0.07
     moc
    -0.07
    moz
    -0.06
     æº
    -0.06
    Occurred
    -0.06
    ueba
    -0.06
    eni
    -0.06
    _Arg
    -0.06
     ninh
    -0.06
    POSITIVE LOGITS
     urban
    0.25
     Urban
    0.21
    urban
    0.21
     city
    0.19
    Urban
    0.19
    -city
    0.17
    éĥ½å¸Ĥ
    0.17
     urb
    0.17
    åŁİå¸Ĥ
    0.16
    city
    0.16
    Activations Density 0.073%

    No Known Activations