© 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. 97760
    Prev
    Next
    INDEX
    Explanations

    references to services, products, and interactions related to transportation and delivery systems

    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
    onen
    -0.08
    ä½
    -0.07
    iew
    -0.07
    _requirements
    -0.07
    meld
    -0.07
    398
    -0.07
    ossa
    -0.07
    vak
    -0.07
    ãĤ¿ãĥ³
    -0.06
    /fw
    -0.06
    POSITIVE LOGITS
     Eh
    0.07
     Wilkinson
    0.06
    resco
    0.06
    avin
    0.06
    ÑĤож
    0.06
    icol
    0.06
    ëª
    0.06
    thers
    0.06
    £¨
    0.05
    UIL
    0.05
    Activations Density 0.121%

    No Known Activations