© 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. 3694
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to individuals' relationships or connections to others

    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
    arkan
    -0.08
    modes
    -0.07
    chia
    -0.06
    ansa
    -0.06
     weather
    -0.06
    andro
    -0.06
    zon
    -0.06
    BN
    -0.06
    973
    -0.06
    actory
    -0.06
    POSITIVE LOGITS
     own
    0.08
     target
    0.07
     itself
    0.07
    _own
    0.06
    own
    0.06
     surroundings
    0.06
     favourite
    0.06
     opponents
    0.06
     Maker
    0.06
    uggy
    0.06
    Activations Density 0.100%

    No Known Activations