© 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. 70416
    Prev
    Next
    INDEX
    Explanations

    expressions related to family and 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
    AREN
    -0.06
    ilot
    -0.06
    ÏģοÏį
    -0.06
    olla
    -0.06
    Incoming
    -0.06
    رج
    -0.06
    anders
    -0.06
    anner
    -0.06
    lesia
    -0.06
    amam
    -0.06
    POSITIVE LOGITS
     Funeral
    0.07
    ofs
    0.06
    gli
    0.06
    /ws
    0.06
    åĿĬ
    0.06
     preceded
    0.06
     ÑģÑĤаÑĢи
    0.06
    preced
    0.06
    ÅĻel
    0.06
     funeral
    0.06
    Activations Density 0.001%

    No Known Activations