© 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. 9-LLAMASCOPE-RES-131K
    11. 97449
    Prev
    Next
    INDEX
    Explanations

    specific property listings related to real estate addresses

    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
    ouro
    -0.08
    strand
    -0.06
    ewan
    -0.06
     ear
    -0.06
    ÑĢежд
    -0.06
    kop
    -0.06
    rabbit
    -0.06
    бÑĥÑĢг
    -0.05
    ":[{↵
    -0.05
    оÑĢож
    -0.05
    POSITIVE LOGITS
    wa
    0.07
    _wo
    0.06
    ENU
    0.06
    ãĥ³ãĥģ
    0.06
     Eh
    0.06
     Nielsen
    0.06
    esson
    0.06
     yans
    0.06
    uz
    0.06
    ogie
    0.06
    Activations Density 0.001%

    No Known Activations