© 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. 75013
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure, particularly related to property accessors

    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
    Cpp
    -0.07
    ERRU
    -0.07
    zo
    -0.07
    ippi
    -0.06
    ills
    -0.06
    /question
    -0.06
    .Unity
    -0.06
    ROT
    -0.06
    ियत
    -0.06
    utra
    -0.06
    POSITIVE LOGITS
     norske
    0.07
    roscope
    0.06
    ideon
    0.06
    èĬ³
    0.06
    720
    0.06
    ãĥĪãĥ«
    0.06
    refs
    0.06
     (*)(
    0.06
    stable
    0.06
    .son
    0.06
    Activations Density 0.002%

    No Known Activations