© 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. 61946
    Prev
    Next
    INDEX
    Explanations

    terms related to data organization and visualization techniques

    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
    åį°
    -0.07
    íĥķ
    -0.07
    à¸ĸม
    -0.06
     Hardcover
    -0.06
     McCart
    -0.06
     assort
    -0.06
     hel
    -0.06
    .Designer
    -0.06
    å®ı
    -0.06
    Stencil
    -0.06
    POSITIVE LOGITS
    ảo
    0.08
     дÑĢÑĥж
    0.06
    .metadata
    0.06
     Scholarship
    0.06
    ascimento
    0.06
    åľ¨çº¿
    0.06
     Scalar
    0.06
    ipt
    0.06
     scholarship
    0.06
    .si
    0.06
    Activations Density 0.003%

    No Known Activations