© 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. 78981
    Prev
    Next
    INDEX
    Explanations

    discussions related to child behavior and parenting challenges

    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
    Ñĥнк
    -0.07
    illez
    -0.07
     orgas
    -0.07
    надлеж
    -0.06
    umo
    -0.06
     khung
    -0.06
     fatt
    -0.06
    quee
    -0.06
    likle
    -0.06
     cuid
    -0.06
    POSITIVE LOGITS
     tantr
    0.07
     temper
    0.07
    geist
    0.07
     Interpreter
    0.06
     temperament
    0.06
     nap
    0.06
     behavior
    0.06
     εν
    0.06
     angel
    0.06
    895
    0.06
    Activations Density 0.030%

    No Known Activations