© 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. 106714
    Prev
    Next
    INDEX
    Explanations

    words related to creation and production

    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
    hive
    -0.06
     Explicit
    -0.06
     Fund
    -0.06
    LETTE
    -0.06
    Ñģли
    -0.06
    urar
    -0.06
    lette
    -0.06
    vro
    -0.06
    urum
    -0.06
     fund
    -0.05
    POSITIVE LOGITS
     automatic
    0.07
    ouz
    0.07
    pects
    0.07
    automatic
    0.06
     ìŀIJëıĻ
    0.06
     integr
    0.06
    apsulation
    0.06
    ucas
    0.06
    rome
    0.06
    Spacing
    0.06
    Activations Density 0.003%

    No Known Activations