© 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. 128875
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing administrative and organizational actions

    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
    _COMPAT
    -0.07
    iedo
    -0.07
    olle
    -0.07
    ovsky
    -0.06
    ména
    -0.06
    urm
    -0.06
     Alley
    -0.06
    лаÑĤи
    -0.06
     Hull
    -0.06
    oland
    -0.06
    POSITIVE LOGITS
    /or
    0.07
    acles
    0.07
    HttpException
    0.07
    iyle
    0.06
    utter
    0.06
     Tau
    0.06
    bah
    0.06
     Nab
    0.06
    raquo
    0.06
    ifice
    0.06
    Activations Density 0.010%

    No Known Activations