© 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. 108203
    Prev
    Next
    INDEX
    Explanations

    names of characters or significant individuals

    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
    opia
    -0.06
    gfx
    -0.06
     carrier
    -0.06
     Borough
    -0.06
     underground
    -0.06
     homelessness
    -0.06
    rens
    -0.06
     cellar
    -0.06
    _recall
    -0.05
    é»İ
    -0.05
    POSITIVE LOGITS
    ĥģ
    0.08
     inn
    0.07
    ä¸ļåĬ¡
    0.07
    /trunk
    0.07
     puan
    0.07
    UGIN
    0.07
    -toggler
    0.07
     âĨĴ↵↵
    0.07
    [property
    0.07
     ìĸ´ëĸ
    0.07
    Activations Density 0.000%

    No Known Activations