© 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. 78429
    Prev
    Next
    INDEX
    Explanations

    phrases related to creativity and design concepts

    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
     Constitutional
    -0.06
    ount
    -0.06
    han
    -0.06
    aryawan
    -0.06
    iciel
    -0.06
     outnumber
    -0.06
    iska
    -0.06
    backup
    -0.06
    enting
    -0.06
     Fame
    -0.06
    POSITIVE LOGITS
     overall
    0.08
     result
    0.08
    agate
    0.07
    :result
    0.07
     resultant
    0.07
    lero
    0.07
    result
    0.07
    OKIE
    0.07
    PELL
    0.07
     risult
    0.06
    Activations Density 0.034%

    No Known Activations