© 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. 95045
    Prev
    Next
    INDEX
    Explanations

    specific dates and times mentioned within the text

    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
    atak
    -0.08
    ampie
    -0.07
    ons
    -0.06
    yn
    -0.06
     fld
    -0.06
    chalk
    -0.06
    ìĿ´ìĬĪ
    -0.06
    çı
    -0.06
    iem
    -0.06
    -alist
    -0.06
    POSITIVE LOGITS
     we
    0.08
    ween
    0.07
    ,exports
    0.07
     thì
    0.07
    appen
    0.07
     Infragistics
    0.07
    人们
    0.06
    fort
    0.06
    æľī人
    0.06
     there
    0.06
    Activations Density 0.032%

    No Known Activations