© 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. 95789
    Prev
    Next
    INDEX
    Explanations

    references to music downloads and sources

    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
    Ë
    -0.07
    ÅĻe
    -0.07
    izu
    -0.07
    oldt
    -0.07
    ILog
    -0.06
    licative
    -0.06
    inite
    -0.06
    asic
    -0.06
    vala
    -0.06
    ifa
    -0.06
    POSITIVE LOGITS
    wdx
    0.07
    sed
    0.07
    hq
    0.07
    SED
    0.06
     electro
    0.06
    ï¼ĮãĢĬ
    0.06
    лиÑĤ
    0.06
    lean
    0.06
    mv
    0.06
    _Api
    0.06
    Activations Density 0.004%

    No Known Activations