© 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. 77783
    Prev
    Next
    INDEX
    Explanations

    words associated with aging and societal issues

    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
    ìļ´
    -0.07
    UDA
    -0.07
    unities
    -0.07
    ë¹Ļ
    -0.07
     ì°½
    -0.07
    _encoding
    -0.06
    isure
    -0.06
    ame
    -0.06
    ijing
    -0.06
    é³´
    -0.06
    POSITIVE LOGITS
     camp
    0.07
     camping
    0.06
    REEN
    0.06
     homeless
    0.06
     Camping
    0.06
     civil
    0.06
     military
    0.06
     confl
    0.06
     camps
    0.06
     enc
    0.06
    Activations Density 0.000%

    No Known Activations