© 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. 94347
    Prev
    Next
    INDEX
    Explanations

    characteristics and descriptions of plants

    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
    iaux
    -0.07
    ombok
    -0.07
    erties
    -0.07
    alim
    -0.07
    lamaz
    -0.07
    deaux
    -0.06
    antino
    -0.06
    sian
    -0.06
    .hom
    -0.06
    isclosed
    -0.06
    POSITIVE LOGITS
    æ²ĸ
    0.07
    ignon
    0.06
    инок
    0.06
     Clone
    0.06
    ä¹
    0.06
    Clone
    0.06
     BaseType
    0.06
    кÑĥÑĤ
    0.06
    erek
    0.06
     departing
    0.06
    Activations Density 0.015%

    No Known Activations