© 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. 55366
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure, particularly in the context of testing functions and policies

    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
    .scalablytyped
    -0.07
    GOR
    -0.06
    phan
    -0.06
    illes
    -0.06
    avigator
    -0.06
    ÅĦ
    -0.06
    lope
    -0.06
    _requires
    -0.06
    ortho
    -0.06
    elight
    -0.06
    POSITIVE LOGITS
    aylight
    0.07
    ertas
    0.07
    linky
    0.06
    们
    0.06
    etsy
    0.06
    kus
    0.06
    ÑģÑĤи
    0.06
    olynomial
    0.06
     Pel
    0.06
    ommen
    0.06
    Activations Density 0.007%

    No Known Activations