© 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. 72591
    Prev
    Next
    INDEX
    Explanations

    terms related to accommodations and facilities

    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
    onga
    -0.08
    allet
    -0.07
    ROLL
    -0.06
    è¡Ĺéģĵ
    -0.06
    ardo
    -0.06
    loff
    -0.06
     Ya
    -0.06
    RIPT
    -0.06
     searchData
    -0.06
    obble
    -0.06
    POSITIVE LOGITS
     moden
    0.07
    ÑģÑİ
    0.06
    inde
    0.06
     equipments
    0.06
    /goto
    0.06
    incare
    0.06
     mutually
    0.06
     thems
    0.06
    Å¡en
    0.06
    pong
    0.06
    Activations Density 0.000%

    No Known Activations