© 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. 29415
    Prev
    Next
    INDEX
    Explanations

    operations related to bit manipulation in code

    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
    clist
    -0.07
    :UITableView
    -0.07
    zych
    -0.07
    зи
    -0.07
    raith
    -0.07
    izin
    -0.07
    --------------------------------------------------------------------------↵
    -0.07
    letal
    -0.06
     closure
    -0.06
    obraz
    -0.06
    POSITIVE LOGITS
    -fe
    0.07
    ĮĢ
    0.06
    ries
    0.06
    ady
    0.06
    GRP
    0.06
     Walnut
    0.06
     Hind
    0.06
    ãĤ¹ãĤ¿ãĥ¼
    0.06
    orex
    0.06
     Syndrome
    0.06
    Activations Density 0.009%

    No Known Activations