© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107239
    Prev
    Next
    INDEX
    Explanations

    instructions regarding the application of topical medications

    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
     approach
    -0.07
     ê
    -0.06
     Thur
    -0.06
     Approach
    -0.06
     camp
    -0.06
     impres
    -0.06
    ugar
    -0.06
     limp
    -0.06
    674
    -0.06
     Auf
    -0.06
    POSITIVE LOGITS
    /application
    0.07
    inea
    0.07
    apon
    0.07
    abled
    0.06
    TPL
    0.06
     unintended
    0.06
     applic
    0.06
    urs
    0.06
    857
    0.06
    ÅĽci
    0.06
    Activations Density 0.019%

    No Known Activations