© 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. 81343
    Prev
    Next
    INDEX
    Explanations

    phrases related to accommodation and other numerical data

    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
    IGINAL
    -0.08
    izr
    -0.07
    iggs
    -0.06
    rens
    -0.06
    ÙħÛĮÙĦ
    -0.06
    \admin
    -0.06
    gii
    -0.06
    swick
    -0.06
    éļ
    -0.06
    lossen
    -0.06
    POSITIVE LOGITS
    uci
    0.07
    lopedia
    0.07
    ouser
    0.06
    .Camera
    0.06
     Polar
    0.06
    inq
    0.06
    дап
    0.06
    amerate
    0.05
     ê·Ģ
    0.05
    arkan
    0.05
    Activations Density 0.000%

    No Known Activations