© 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. 5-LLAMASCOPE-RES-131K
    11. 126705
    Prev
    Next
    INDEX
    Explanations

    words related to negative conditions or problems

    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
     or
    -0.09
    sville
    -0.07
    ADDE
    -0.07
     and
    -0.06
    avras
    -0.06
    elez
    -0.06
     Kane
    -0.06
    kin
    -0.06
     onBind
    -0.06
     parent
    -0.06
    POSITIVE LOGITS
    loadModel
    0.07
    /etc
    0.06
    poÄįet
    0.06
     åħ
    0.06
     Dön
    0.06
    ï¼ĪæĺŃåĴĮ
    0.06
     деп
    0.06
    emu
    0.06
    parity
    0.06
    LastError
    0.06
    Activations Density 0.077%

    No Known Activations