© 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. 87738
    Prev
    Next
    INDEX
    Explanations

    numerical figures and references related to time periods or quantities

    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
    .heroku
    -0.08
    /***/
    -0.08
    _INTR
    -0.07
    ãĤĵãģ¨
    -0.07
    QualifiedName
    -0.07
    çek
    -0.07
     Invasion
    -0.07
    .libs
    -0.07
     ÄĮeská
    -0.07
    .AppSettings
    -0.07
    POSITIVE LOGITS
    ardin
    0.06
    wan
    0.06
    APON
    0.06
    ecies
    0.06
    ce
    0.06
    ards
    0.06
     Caldwell
    0.06
    Winvalid
    0.06
     caul
    0.06
    ±ä¹IJ
    0.05
    Activations Density 0.029%

    No Known Activations