© 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. 97654
    Prev
    Next
    INDEX
    Explanations

    HTML tags and other markup elements

    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
     ÑĨим
    -0.06
    dn
    -0.06
    isto
    -0.06
    [end
    -0.06
     Dale
    -0.06
    asse
    -0.06
     Scotia
    -0.06
    uge
    -0.06
     Clay
    -0.06
    terminal
    -0.05
    POSITIVE LOGITS
     tread
    0.07
     cryst
    0.06
     tavs
    0.06
    ÑĦоÑĢми
    0.06
     elev
    0.06
     rfl
    0.06
    rane
    0.06
     Nev
    0.06
    lex
    0.05
    orris
    0.05
    Activations Density 0.001%

    No Known Activations