© 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 EvalsExportsAPI 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. 128928
    Prev
    Next
    INDEX
    Explanations

    terms related to optionality and nullable types in programming

    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
    лÑĥж
    -0.07
    ãģĿãģĨãģª
    -0.06
    ãģĭãĤı
    -0.06
    æİĴ
    -0.06
    ÑĥÑī
    -0.06
    gtest
    -0.06
    din
    -0.06
    ìĭľìķĦ
    -0.06
    (constants
    -0.06
    reau
    -0.06
    POSITIVE LOGITS
    olini
    0.07
    atoi
    0.06
    838
    0.06
    oren
    0.06
    graded
    0.06
    ome
    0.06
     Hood
    0.06
     graded
    0.06
    .prof
    0.06
     Til
    0.06
    Activations Density 0.001%

    No Known Activations