© 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. 129919
    Prev
    Next
    INDEX
    Explanations

    references to cybercrime and legal terms related to property rights

    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
    ureau
    -0.06
     Tray
    -0.06
    atar
    -0.06
    vig
    -0.06
     deform
    -0.06
    ansson
    -0.06
    ournals
    -0.06
     cl
    -0.06
    ÑħÑĥ
    -0.06
     uni
    -0.06
    POSITIVE LOGITS
    owi
    0.08
    è´¨
    0.07
    ouser
    0.06
    éĿł
    0.06
    .metric
    0.06
    afone
    0.06
    quoi
    0.06
    اذ
    0.06
    _SSL
    0.06
    ault
    0.06
    Activations Density 0.003%

    No Known Activations