© 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. 15-LLAMASCOPE-RES-131K
    11. 88107
    Prev
    Next
    INDEX
    Explanations

    information regarding accommodations and amenities in a specific location

    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
    tek
    -0.08
    arkin
    -0.08
    mÃŃn
    -0.07
    eldon
    -0.07
    UPI
    -0.07
     Duffy
    -0.07
    antino
    -0.07
    allet
    -0.07
    ãĥ¼ãĥī
    -0.06
    rana
    -0.06
    POSITIVE LOGITS
    omatic
    0.06
     Bund
    0.06
    .Bundle
    0.06
    aru
    0.06
    eting
    0.06
     Lou
    0.06
    OM
    0.06
     Buckley
    0.06
    amus
    0.06
    oma
    0.05
    Activations Density 0.008%

    No Known Activations