© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 107314
    Prev
    Next
    INDEX
    Explanations

    specific dates and error messages related to computer issues

    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
    ãĥ©ãĥ¼
    -0.07
    ubic
    -0.06
    ATS
    -0.06
    Paint
    -0.06
    aus
    -0.06
    atcher
    -0.06
    ÑĤеÑĢ
    -0.06
    ru
    -0.06
    ukt
    -0.06
    ttp
    -0.06
    POSITIVE LOGITS
    uzzi
    0.07
     Tee
    0.06
    apur
    0.06
    æľĽ
    0.06
     ÙħÛĮÙĦادÛĮ
    0.06
    hm
    0.06
    forman
    0.06
    rente
    0.06
    andes
    0.06
     Amerikan
    0.06
    Activations Density 0.001%

    No Known Activations