© 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 EvalsExportsinterp-engineNEWAPI 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. 31153
    Prev
    Next
    INDEX
    Explanations

    references to teaching, learning, and religious themes

    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
    deaux
    -0.08
    portlet
    -0.07
    _FAR
    -0.07
    à¸ļรร
    -0.07
    isclosed
    -0.07
    quette
    -0.07
     penn
    -0.07
    peq
    -0.07
    flip
    -0.07
    ouri
    -0.07
    POSITIVE LOGITS
     Silver
    0.07
    ilde
    0.07
    Silver
    0.06
    Tim
    0.06
     Kop
    0.06
     Tit
    0.06
    025
    0.06
     Paul
    0.06
     Sag
    0.06
    udi
    0.06
    Activations Density 0.003%

    No Known Activations