© 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. 94784
    Prev
    Next
    INDEX
    Explanations

    topics related to cybersecurity and its implications for healthcare

    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
    ameda
    -0.08
    ãĢĶ
    -0.07
    ầm
    -0.07
    agini
    -0.07
     dag
    -0.07
    (æ°´
    -0.07
    ÙĦØ·
    -0.07
    SPATH
    -0.07
     ÑĥÑģÑĤ
    -0.06
    OwnProperty
    -0.06
    POSITIVE LOGITS
    arel
    0.07
     consum
    0.06
    ennie
    0.06
    typings
    0.05
     Article
    0.05
     Cardinal
    0.05
    886
    0.05
    arios
    0.05
    uae
    0.05
    harma
    0.05
    Activations Density 0.011%

    No Known Activations