© 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. 87518
    Prev
    Next
    INDEX
    Explanations

    references to web development languages and files

    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
     ç¤
    -0.08
    uli
    -0.07
    UNET
    -0.07
    omer
    -0.07
    yonel
    -0.07
    bulan
    -0.07
    ensen
    -0.07
    immer
    -0.07
    stad
    -0.07
    lecture
    -0.07
    POSITIVE LOGITS
    碼
    0.07
    ëªħìĿĺ
    0.07
     Sergio
    0.06
     Setter
    0.06
    ãĥªãĥ¼ãĤº
    0.06
    кÑĢа
    0.06
    âĺĨ
    0.06
     bob
    0.06
     vÃŃ
    0.06
    panic
    0.06
    Activations Density 0.001%

    No Known Activations