© 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. 125570
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "my" and other possessive references within a programming context

    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
     Kinh
    -0.07
    creativecommons
    -0.06
    ucc
    -0.06
    Å¡ti
    -0.06
    -placeholder
    -0.06
    lood
    -0.06
    hu
    -0.06
    æ³ī
    -0.06
    пÑĢав
    -0.06
     Nunes
    -0.06
    POSITIVE LOGITS
    kaar
    0.07
     عÙħÙĦ
    0.06
    \:
    0.06
    ãĦ
    0.06
    .ul
    0.06
    ?action
    0.06
    egis
    0.06
    readcr
    0.06
    igans
    0.06
     øns
    0.06
    Activations Density 0.039%

    No Known Activations