© 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. 17-LLAMASCOPE-RES-131K
    11. 82218
    Prev
    Next
    INDEX
    Explanations

    transportation routes involving Detroit and other cities

    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
    æŀĿ
    -0.07
    uffman
    -0.07
     attachments
    -0.06
    ury
    -0.06
    mailbox
    -0.06
    обов
    -0.06
    Äįi
    -0.06
     ↵↵
    -0.06
     compound
    -0.06
    rita
    -0.06
    POSITIVE LOGITS
    ATES
    0.08
    ates
    0.07
    ãģŁãģĹ
    0.07
     âĨĶ
    0.07
     ConfigureServices
    0.06
    acent
    0.06
    oppers
    0.06
     âĶľ
    0.06
    -responsive
    0.06
    adero
    0.06
    Activations Density 0.006%

    No Known Activations