© 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. 9-LLAMASCOPE-RES-131K
    11. 96435
    Prev
    Next
    INDEX
    Explanations

    references to possessive pronouns and related possessive constructs

    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
    752
    -0.07
    essen
    -0.06
     Shapiro
    -0.06
    elles
    -0.06
    inz
    -0.06
    arat
    -0.06
    igrams
    -0.06
    ella
    -0.06
    una
    -0.06
     Dunk
    -0.06
    POSITIVE LOGITS
    ĥn
    0.07
     inventor
    0.06
     isp
    0.06
     Hum
    0.06
    á»Ļi
    0.06
     nackt
    0.06
    .Ticks
    0.06
    Äįit
    0.06
    Å¡tÄĽ
    0.06
    ames
    0.06
    Activations Density 0.021%

    No Known Activations