© 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. 72416
    Prev
    Next
    INDEX
    Explanations

    programming-related function calls and syntax elements

    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
    ---</
    -0.08
    .scalablytyped
    -0.07
     Bölüm
    -0.07
    ụn
    -0.07
    -------------</
    -0.07
    .SizeType
    -0.07
    Ñĥки
    -0.07
    ActionCreators
    -0.07
     -*-č↵
    -0.07
    κÎŃ
    -0.07
    POSITIVE LOGITS
    žÃŃ
    0.06
    ownt
    0.06
    ario
    0.06
     Zu
    0.06
    kur
    0.06
    GH
    0.06
    mus
    0.06
     Kun
    0.05
    åĭ
    0.05
    istribute
    0.05
    Activations Density 0.152%

    No Known Activations