© 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. 92964
    Prev
    Next
    INDEX
    Explanations

    references to creative projects and events

    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
    cala
    -0.07
    niej
    -0.07
     arada
    -0.07
    .BLL
    -0.06
    лам
    -0.06
     ?>"/>↵
    -0.06
    alth
    -0.06
    avad
    -0.06
    hints
    -0.06
    UILDER
    -0.06
    POSITIVE LOGITS
     hereby
    0.07
    gui
    0.07
    YPRE
    0.07
    SCII
    0.06
    .gb
    0.06
    bz
    0.06
    ãĤĬãģ¨
    0.06
    597
    0.06
    844
    0.06
    595
    0.06
    Activations Density 0.033%

    No Known Activations