© 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. 56144
    Prev
    Next
    INDEX
    Explanations

    references to love and its implications within a moral or ethical context

    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
    аÑĢÑĮ
    -0.07
    tk
    -0.06
    ius
    -0.06
    .DAL
    -0.06
    ĺ
    -0.06
    irable
    -0.06
    ιά
    -0.06
    teri
    -0.06
    ESIS
    -0.06
    vrd
    -0.06
    POSITIVE LOGITS
    atos
    0.08
    zeigt
    0.07
     Dem
    0.07
    Ãło
    0.06
    inton
    0.06
    osten
    0.06
    standen
    0.06
    áo
    0.06
    оÑĤоÑĢ
    0.06
    erton
    0.06
    Activations Density 0.093%

    No Known Activations