© 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. 27746
    Prev
    Next
    INDEX
    Explanations

    historical timelines and references to art movements across different periods

    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
    .hw
    -0.08
    ãĥªãĤ«
    -0.08
    /stdc
    -0.08
    hurst
    -0.07
    gan
    -0.07
    aÄį
    -0.07
    ucas
    -0.07
    ãģĨãģ¡
    -0.07
    /renderer
    -0.07
    оÑĢаз
    -0.07
    POSITIVE LOGITS
     today
    0.12
     present
    0.11
     recent
    0.10
     contemporary
    0.10
     modern
    0.09
     latest
    0.09
     Present
    0.09
     presente
    0.09
     current
    0.09
    today
    0.09
    Activations Density 0.012%

    No Known Activations