© 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. 95348
    Prev
    Next
    INDEX
    Explanations

    references to entities and compliance in healthcare and regulatory contexts

    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
    pus
    -0.07
    erne
    -0.06
    illac
    -0.06
    //--
    -0.06
    izza
    -0.06
    avel
    -0.06
     Král
    -0.06
     Defensive
    -0.05
     unconstitutional
    -0.05
    aset
    -0.05
    POSITIVE LOGITS
     whose
    0.07
    etics
    0.07
    uais
    0.07
    whose
    0.07
    uant
    0.07
    ennon
    0.06
    oster
    0.06
    ä¸įå¾Ĺ
    0.06
    ickers
    0.06
    à¹īว
    0.06
    Activations Density 0.018%

    No Known Activations