© 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. 86184
    Prev
    Next
    INDEX
    Explanations

    references to specific model years of cars

    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
    append
    -0.07
    é»
    -0.06
     append
    -0.06
    <main
    -0.06
    duct
    -0.06
    ecess
    -0.06
     libr
    -0.06
    inaire
    -0.05
    ws
    -0.05
    asters
    -0.05
    POSITIVE LOGITS
    tach
    0.08
     Westminster
    0.07
    átka
    0.06
    aska
    0.06
    ÑģиÑĤ
    0.06
    istro
    0.06
    iolet
    0.06
    atre
    0.06
    yr
    0.06
     âĨĵ
    0.06
    Activations Density 0.004%

    No Known Activations