© 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. 15-LLAMASCOPE-RES-131K
    11. 87559
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to boating and waterfront properties

    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
    licit
    -0.06
    Rooms
    -0.06
     kari
    -0.06
    routes
    -0.06
     Rooms
    -0.06
    ledon
    -0.06
     è¾
    -0.06
    sons
    -0.06
    junction
    -0.06
     Farms
    -0.06
    POSITIVE LOGITS
     fee
    0.09
     Fee
    0.08
    .storage
    0.07
    uhl
    0.07
     fees
    0.07
    ithe
    0.07
    (storage
    0.07
    avad
    0.07
    uby
    0.06
     STORAGE
    0.06
    Activations Density 0.003%

    No Known Activations