© 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 EvalsExportsAPI 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. 128932
    Prev
    Next
    INDEX
    Explanations

    references to luxury accommodations and products

    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
    sdale
    -0.08
    chu
    -0.07
     thù
    -0.07
    czy
    -0.07
    uncan
    -0.07
    fty
    -0.07
    -called
    -0.07
    nie
    -0.06
    athon
    -0.06
    ew
    -0.06
    POSITIVE LOGITS
    urious
    0.11
    -minded
    0.09
    zed
    0.08
    tainment
    0.08
    ariant
    0.08
    uries
    0.08
    EDA
    0.07
    erner
    0.07
     minded
    0.07
    ContextHolder
    0.07
    Activations Density 0.005%

    No Known Activations