© 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. 29051
    Prev
    Next
    INDEX
    Explanations

    pronouns related to ownership and possession

    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
    quate
    -0.06
    arness
    -0.06
    othy
    -0.06
    owied
    -0.06
     Baron
    -0.06
    asic
    -0.06
    reib
    -0.06
    oft
    -0.06
    orra
    -0.06
     glove
    -0.06
    POSITIVE LOGITS
     behalf
    0.13
     occasion
    0.07
    lv
    0.07
    ollar
    0.07
    lap
    0.06
    pector
    0.06
    screen
    0.06
     lap
    0.06
    227
    0.06
     radar
    0.06
    Activations Density 0.031%

    No Known Activations