© 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. 40395
    Prev
    Next
    INDEX
    Explanations

    possessive forms and phrases indicating ownership or experiences

    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
    NESS
    -0.07
     Ñĩеловек
    -0.07
     itself
    -0.07
    enÄĽ
    -0.07
    елов
    -0.07
    agrid
    -0.07
    ulumi
    -0.07
     sám
    -0.07
    InstanceOf
    -0.07
    ivial
    -0.06
    POSITIVE LOGITS
     minds
    0.09
     themselves
    0.09
     lives
    0.08
     efforts
    0.08
     hearts
    0.07
    ongyang
    0.07
     rights
    0.07
     choices
    0.07
     favorite
    0.07
     ability
    0.07
    Activations Density 0.022%

    No Known Activations