© 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. 40390
    Prev
    Next
    INDEX
    Explanations

    programming constructs and method calls related to object initialization

    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
    itect
    -0.07
    ussen
    -0.06
     closure
    -0.06
    itto
    -0.06
    inary
    -0.06
    define
    -0.06
    ÄįnÃŃk
    -0.06
    ional
    -0.06
    anj
    -0.06
    boo
    -0.06
    POSITIVE LOGITS
    .getSystemService
    0.07
    PermissionsResult
    0.06
    WithOptions
    0.06
    OrFail
    0.06
    ç¿Ķ
    0.06
    ë£Į
    0.06
    antz
    0.06
    Dll
    0.06
    (typeof
    0.06
    SystemService
    0.06
    Activations Density 0.001%

    No Known Activations