© 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. 39127
    Prev
    Next
    INDEX
    Explanations

    details related to home features and real estate descriptions

    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
    iag
    -0.06
    atorium
    -0.06
    agma
    -0.06
    lea
    -0.06
    ila
    -0.06
    /*č↵
    -0.06
    uggage
    -0.06
     etc
    -0.06
    æ²»
    -0.06
    errick
    -0.05
    POSITIVE LOGITS
     McCart
    0.07
    úsqueda
    0.07
    ÑĨин
    0.07
     Punch
    0.07
    QRST
    0.07
    ายà¸Ļ
    0.07
     Blanch
    0.07
    -flow
    0.07
     punched
    0.07
    å¹³æĪIJ
    0.07
    Activations Density 0.036%

    No Known Activations