© 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. 9-LLAMASCOPE-RES-131K
    11. 97396
    Prev
    Next
    INDEX
    Explanations

    elements and methods related to document manipulation in web development

    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
    isay
    -0.06
    anou
    -0.06
    azzi
    -0.06
    bjerg
    -0.06
     exist
    -0.06
    itia
    -0.06
     Cly
    -0.06
     åį
    -0.06
    ascus
    -0.05
    fec
    -0.05
    POSITIVE LOGITS
    isol
    0.07
    ghan
    0.07
    oyo
    0.07
    ανδ
    0.07
    urret
    0.07
    ingo
    0.07
    ulling
    0.07
    ãĥ³ãĥģ
    0.06
    IMATE
    0.06
     academia
    0.06
    Activations Density 0.046%

    No Known Activations