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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125469
    Prev
    Next
    INDEX
    Explanations

    geographic locations and their attributes

    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
    folio
    -0.07
    ıcı
    -0.07
    ogue
    -0.07
    evi
    -0.07
    emme
    -0.07
    oine
    -0.07
    uffman
    -0.06
    locator
    -0.06
    .Guna
    -0.06
    zej
    -0.06
    POSITIVE LOGITS
     County
    0.09
     Counties
    0.09
     counties
    0.09
     окÑĢÑĥг
    0.09
     Province
    0.09
     county
    0.08
    eshire
    0.08
     province
    0.08
     District
    0.07
    consin
    0.07
    Activations Density 0.078%

    No Known Activations