© 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. 29342
    Prev
    Next
    INDEX
    Explanations

    pronouns that indicate possession or ownership

    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
     invol
    -0.06
    naÄį
    -0.06
    kke
    -0.06
    puter
    -0.06
    ÑĢÑıд
    -0.06
    /Instruction
    -0.06
    avou
    -0.06
    ONO
    -0.06
    sembly
    -0.06
    ÙĪÙħات
    -0.06
    POSITIVE LOGITS
     own
    0.11
     Own
    0.07
    own
    0.07
    iglia
    0.07
     próp
    0.07
     OWN
    0.07
    Own
    0.07
    ieves
    0.07
    Advertisement
    0.06
    CLU
    0.06
    Activations Density 0.018%

    No Known Activations