© 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. 89055
    Prev
    Next
    INDEX
    Explanations

    elements related to customer service and job application mechanics

    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
    uffer
    -0.06
    -0.06
     lif
    -0.06
    ExecutionContext
    -0.06
     Lv
    -0.06
    gam
    -0.05
     cann
    -0.05
     multiple
    -0.05
    atch
    -0.05
    ,
    -0.05
    POSITIVE LOGITS
    GLE
    0.07
    éŁ¿
    0.07
    bast
    0.07
    ÙĬÙħÙĬ
    0.07
    ÑģоÑĤ
    0.07
    /gpl
    0.07
    /epl
    0.07
     #__
    0.07
    ãĢģé«ĺ
    0.07
    à¸Ļà¸ķ
    0.07
    Activations Density 0.011%

    No Known Activations