© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29969
    Prev
    Next
    INDEX
    Explanations

    function calls and references to object properties 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
    ì´Ī
    -0.07
     ãĤ±
    -0.06
    POCH
    -0.06
    ableView
    -0.06
     Nhĩ
    -0.06
    ymm
    -0.06
    ÙIJÙij
    -0.06
    ivia
    -0.06
    .getSeconds
    -0.06
     erót
    -0.06
    POSITIVE LOGITS
     whose
    0.07
    byname
    0.07
    stantiateViewController
    0.07
    .ZERO
    0.06
     suff
    0.06
     MainForm
    0.06
     Hats
    0.06
     tre
    0.06
     Downing
    0.06
    ("
    0.06
    Activations Density 0.025%

    No Known Activations