© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86463
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on" in various contexts

    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
    ioxide
    -0.07
    raphics
    -0.06
     offic
    -0.06
    elper
    -0.06
    (+
    -0.06
     incontr
    -0.06
     HQ
    -0.06
    TRA
    -0.06
    лаÑĩ
    -0.06
    ãģ¨ãģĦ
    -0.06
    POSITIVE LOGITS
    ymoon
    0.07
    nob
    0.06
    ichtet
    0.06
     phá»ij
    0.06
    vanished
    0.06
     Wikimedia
    0.06
    anian
    0.06
    raya
    0.06
    skirts
    0.06
    inea
    0.06
    Activations Density 0.003%

    No Known Activations