© 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. 117773
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to residential buildings and housing conditions

    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
    $MESS
    -0.06
     rides
    -0.06
    zem
    -0.06
    ucid
    -0.06
    ादन
    -0.06
     teb
    -0.06
    nerg
    -0.06
    vl
    -0.06
    nem
    -0.06
    roys
    -0.06
    POSITIVE LOGITS
    achuset
    0.08
    oop
    0.07
     пÑĢеÑģÑĤ
    0.07
    INESS
    0.07
     built
    0.07
    .house
    0.07
    /home
    0.07
    ÚĨار
    0.07
    سازÛĮ
    0.07
    atchet
    0.07
    Activations Density 0.039%

    No Known Activations