© 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. 17648
    Prev
    Next
    INDEX
    Explanations

    references to artistic organizations and contributions

    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
    _FA
    -0.07
    ichever
    -0.07
    EXTERNAL
    -0.07
     tisk
    -0.07
    ãĤ¢ãĥ³
    -0.06
    ãħ
    -0.06
    TexParameter
    -0.06
    alf
    -0.06
    coord
    -0.06
     klub
    -0.06
    POSITIVE LOGITS
     worldwide
    0.08
     world
    0.07
     national
    0.07
    ispers
    0.07
     World
    0.07
     American
    0.07
     United
    0.06
     TED
    0.06
    -world
    0.06
    world
    0.06
    Activations Density 0.033%

    No Known Activations