© 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 EvalsExportsinterp-engineNEWAPI 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. 107694
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional or personal conflict in relationships

    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
    outine
    -0.07
    Advertisement
    -0.07
     XK
    -0.07
    iddi
    -0.07
    istrovstvÃŃ
    -0.06
     BindingFlags
    -0.06
    lang
    -0.06
    ragen
    -0.06
    loi
    -0.06
     дела
    -0.06
    POSITIVE LOGITS
    é¼
    0.06
     Vul
    0.06
     cerc
    0.06
    FY
    0.06
    azel
    0.06
    icorn
    0.06
    isode
    0.06
    insky
    0.06
    nze
    0.06
    akes
    0.06
    Activations Density 0.001%

    No Known Activations