© 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. 130915
    Prev
    Next
    INDEX
    Explanations

    medical conditions and their associations with infections or treatment 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
    anse
    -0.08
    anager
    -0.08
    zas
    -0.07
    одо
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    .onStart
    -0.07
    ache
    -0.07
     distracting
    -0.07
    throat
    -0.07
    _zeros
    -0.06
    POSITIVE LOGITS
     repeated
    0.09
     Habit
    0.08
     zbyt
    0.08
     prolonged
    0.07
     too
    0.07
    Repeated
    0.07
     habit
    0.07
    ãģĻãģİ
    0.06
     or
    0.06
    è¿ĩ
    0.06
    Activations Density 0.033%

    No Known Activations