© 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. 62822
    Prev
    Next
    INDEX
    Explanations

    information related to household demographics and living arrangements

    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
     Gui
    -0.06
     Gus
    -0.06
    vas
    -0.06
    ãĥªãĥ¼ãĤº
    -0.06
    ény
    -0.06
     Kız
    -0.06
    .Async
    -0.06
    /gui
    -0.06
    ogui
    -0.06
    Äıte
    -0.06
    POSITIVE LOGITS
    deen
    0.06
     ancestral
    0.06
    ìĹ
    0.06
    (*)(
    0.06
     Mobility
    0.06
     older
    0.06
    itta
    0.06
     whose
    0.06
    Tube
    0.06
     helf
    0.06
    Activations Density 0.001%

    No Known Activations