© 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 EvalsExportsinterp-engineNEWAPI 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. 15146
    Prev
    Next
    INDEX
    Explanations

    words and pronouns related to 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
    sburg
    -0.07
    zsche
    -0.07
    s
    -0.07
    ãĥĥãĤ¯
    -0.07
    inand
    -0.06
    ¸ı
    -0.06
    nts
    -0.06
    amac
    -0.06
     понима
    -0.06
    /TT
    -0.06
    POSITIVE LOGITS
    sing
    0.08
    zelf
    0.07
     own
    0.07
    .spin
    0.07
    OWN
    0.07
    elt
    0.07
    /her
    0.07
    Ùijا
    0.07
    -même
    0.07
    panic
    0.07
    Activations Density 0.011%

    No Known Activations