© 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. 81709
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to product availability and sales information

    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
    .gs
    -0.08
    inker
    -0.07
     behalf
    -0.06
    ÑĢади
    -0.06
     organ
    -0.06
     फर
    -0.06
    ETO
    -0.06
     Shelf
    -0.06
    UIT
    -0.06
    ves
    -0.06
    POSITIVE LOGITS
    586
    0.08
    æĢ§
    0.07
    ãģŁãĤĬ
    0.06
    inel
    0.06
    iring
    0.06
    amodel
    0.06
    ıklı
    0.06
     RIGHT
    0.06
    epam
    0.06
    476
    0.06
    Activations Density 0.012%

    No Known Activations