© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3789
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and court jurisdictions

    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
    ÅĻel
    -0.07
    оÑĢон
    -0.07
    ιά
    -0.07
    dl
    -0.06
    ottes
    -0.06
    ARB
    -0.06
    kdir
    -0.06
     lá»įc
    -0.06
    blr
    -0.06
    usb
    -0.06
    POSITIVE LOGITS
     District
    0.10
     district
    0.10
     districts
    0.09
    District
    0.08
    district
    0.08
    most
    0.08
    _district
    0.08
    CAC
    0.07
    affen
    0.07
     circuit
    0.07
    Activations Density 0.003%

    No Known Activations