© 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. 129310
    Prev
    Next
    INDEX
    Explanations

    code elements related to object properties and methods 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
    abis
    -0.07
    Ñģам
    -0.07
    erdale
    -0.07
    antium
    -0.06
    eneric
    -0.06
    odont
    -0.06
    arend
    -0.06
    UNET
    -0.06
    eah
    -0.06
    ungs
    -0.06
    POSITIVE LOGITS
    kker
    0.07
    IntervalSince
    0.06
    enge
    0.06
    lify
    0.06
     bande
    0.06
    604
    0.06
    agner
    0.06
    619
    0.06
    ervo
    0.06
    agger
    0.06
    Activations Density 0.126%

    No Known Activations