© 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. 15-LLAMASCOPE-RES-131K
    11. 87753
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and elements often associated with web content

    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
     Amerikan
    -0.07
     Caller
    -0.07
    otos
    -0.06
    erdem
    -0.06
    æ¼¢
    -0.06
    [of
    -0.06
    engin
    -0.06
    паÑĤ
    -0.06
    åŀĤ
    -0.06
    dden
    -0.06
    POSITIVE LOGITS
    StartPosition
    0.07
    eroon
    0.07
    gars
    0.06
    recipes
    0.06
    BindingUtil
    0.06
    lez
    0.06
    cha
    0.06
    ahoma
    0.06
     Yao
    0.06
    ait
    0.06
    Activations Density 0.001%

    No Known Activations