© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28543
    Prev
    Next
    INDEX
    Explanations

    instances of geographic locations related to proximity to bodies of water

    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
    ughs
    -0.07
    _fds
    -0.07
    -Cs
    -0.07
    uestion
    -0.07
    istor
    -0.06
    otte
    -0.06
    RequestMethod
    -0.06
    terra
    -0.06
    ÑĤÑĢон
    -0.06
    amina
    -0.06
    POSITIVE LOGITS
     coast
    0.07
     shore
    0.06
    Ấ
    0.06
     port
    0.06
     Tory
    0.06
    jec
    0.06
    義
    0.06
    QL
    0.06
    drag
    0.06
    redo
    0.06
    Activations Density 0.004%

    No Known Activations