© 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. 15-LLAMASCOPE-RES-131K
    11. 88380
    Prev
    Next
    INDEX
    Explanations

    terms related to medical diagnoses and their complexities

    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
    onga
    -0.07
    assi
    -0.07
    vary
    -0.06
    adic
    -0.06
    structions
    -0.06
    iali
    -0.06
     Lun
    -0.06
     nackte
    -0.06
    iry
    -0.06
    mia
    -0.06
    POSITIVE LOGITS
    529
    0.06
    apon
    0.06
    วร
    0.06
    èĢ³
    0.06
    emouth
    0.06
     bailout
    0.06
    /spec
    0.06
    lops
    0.06
    antry
    0.06
    erot
    0.06
    Activations Density 0.017%

    No Known Activations