© 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. 27667
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to nursing and healthcare practices

    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
    esus
    -0.06
     tradition
    -0.06
     wonder
    -0.06
     pint
    -0.05
     Setter
    -0.05
    .RowHeaders
    -0.05
    acob
    -0.05
     displ
    -0.05
    bjerg
    -0.05
    bourg
    -0.05
    POSITIVE LOGITS
     techniques
    0.09
    ãĥ¼ãĥ«
    0.08
     concepts
    0.08
    ãĥ¼ãĥĹ
    0.07
     Techniques
    0.07
    ादन
    0.07
    features
    0.07
    feb
    0.07
     Concepts
    0.07
     Leopard
    0.07
    Activations Density 0.023%

    No Known Activations