© 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. 85288
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical diagnoses and health conditions

    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
    ìĦľëĬĶ
    -0.08
    frey
    -0.08
    à¹Ĩ
    -0.07
    دÙħ
    -0.07
    alim
    -0.07
    ẻ
    -0.07
    mess
    -0.07
    igham
    -0.06
    ofil
    -0.06
    frei
    -0.06
    POSITIVE LOGITS
     Conveyor
    0.06
     with
    0.06
    ATUS
    0.06
    ÑīÑĸ
    0.06
     diagnosed
    0.06
     Bruno
    0.06
     Byl
    0.06
    784
    0.06
    agnost
    0.06
     diagn
    0.06
    Activations Density 0.003%

    No Known Activations