© 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 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. 82972
    Prev
    Next
    INDEX
    Explanations

    occurrences of PHP file references within the text

    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
    rado
    -0.07
    елÑĮно
    -0.06
    eam
    -0.06
     mistr
    -0.06
     Möglichkeit
    -0.06
    inja
    -0.06
    rouw
    -0.06
     POSSIBILITY
    -0.06
    Journal
    -0.06
    ãĤ¥
    -0.06
    POSITIVE LOGITS
    reesome
    0.07
    isode
    0.07
    724
    0.07
    ÑĪÑĤов
    0.07
    кав
    0.07
    atsapp
    0.07
    ovable
    0.06
    urator
    0.06
     WPARAM
    0.06
    ï¸ı
    0.06
    Activations Density 0.004%

    No Known Activations