© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103205
    Prev
    Next
    INDEX
    Explanations

    occurrences of actions or events related to people in various situations

    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
    .eth
    -0.07
    uelles
    -0.07
    æĺĮ
    -0.07
    gili
    -0.07
    ãģijãĤĮãģ°
    -0.07
    QUIRE
    -0.07
    onta
    -0.07
    pla
    -0.07
    ongyang
    -0.06
    kı
    -0.06
    POSITIVE LOGITS
     attempting
    0.07
     trying
    0.07
     Trying
    0.06
     actively
    0.06
     Attempt
    0.06
     attempt
    0.06
    /provider
    0.06
    elpers
    0.06
    _inches
    0.06
     attempts
    0.06
    Activations Density 0.025%

    No Known Activations