© 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. 56908
    Prev
    Next
    INDEX
    Explanations

    words related to packaging and transformation processes

    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
    888
    -0.06
    iece
    -0.06
     testim
    -0.06
    InMillis
    -0.06
    ussy
    -0.06
    672
    -0.06
    Ñij
    -0.06
    ël
    -0.06
    รà¸ģ
    -0.06
    469
    -0.06
    POSITIVE LOGITS
    olia
    0.07
    WithContext
    0.07
    weise
    0.07
    .newaxis
    0.07
     together
    0.06
     with
    0.06
    argest
    0.06
    own
    0.06
    pecting
    0.06
    chod
    0.06
    Activations Density 0.041%

    No Known Activations