© 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. 124809
    Prev
    Next
    INDEX
    Explanations

    topics related to business and industries

    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
    ourg
    -0.08
    abus
    -0.07
    ihar
    -0.06
    rema
    -0.06
    hang
    -0.06
    eldon
    -0.06
    /non
    -0.06
    izza
    -0.06
    avier
    -0.06
    .LookAndFeel
    -0.06
    POSITIVE LOGITS
    ISON
    0.06
     mädchen
    0.06
    å¼ķ
    0.06
    ëĿ¼ëĬĶ
    0.06
    /logging
    0.06
     ÙĤرآÙĨ
    0.06
    _WINDOWS
    0.06
     Consent
    0.06
     chic
    0.06
     software
    0.06
    Activations Density 0.100%

    No Known Activations