© 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. 73656
    Prev
    Next
    INDEX
    Explanations

    keywords related to medical conditions and treatments

    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
    ses
    -0.08
    xes
    -0.08
    ongsTo
    -0.07
    гоÑĢ
    -0.07
    RIORITY
    -0.07
    deo
    -0.07
     toxicity
    -0.07
     unr
    -0.06
    ALLERY
    -0.06
    برÛĮ
    -0.06
    POSITIVE LOGITS
    eous
    0.08
    aneous
    0.07
    ly
    0.07
    ï¸ı
    0.07
    al
    0.07
    aire
    0.06
    gnore
    0.06
     Assets
    0.06
    ous
    0.06
    ãģĭãģij
    0.06
    Activations Density 0.096%

    No Known Activations