© 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. 54910
    Prev
    Next
    INDEX
    Explanations

    concepts related to medical research and antibacterial properties

    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
    urge
    -0.07
    vie
    -0.07
    ãĥĸãĥª
    -0.06
    ifar
    -0.06
     mest
    -0.06
    ENU
    -0.06
    _regs
    -0.06
    decorators
    -0.06
    ->
    -0.06
     practices
    -0.06
    POSITIVE LOGITS
     kills
    0.10
    æĿĢ
    0.08
     Kills
    0.08
     kill
    0.08
    kill
    0.08
     killing
    0.08
    Gram
    0.08
    kills
    0.08
     MIC
    0.07
     Gram
    0.07
    Activations Density 0.025%

    No Known Activations