© 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. 61873
    Prev
    Next
    INDEX
    Explanations

    phrases indicating 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
    ÙĪاز
    -0.06
    PathParam
    -0.06
    ÙĬØ©
    -0.06
    kop
    -0.06
    iets
    -0.06
    lux
    -0.06
    /fixtures
    -0.06
    oy
    -0.06
    à¥Ģण
    -0.06
    abet
    -0.06
    POSITIVE LOGITS
     meaning
    0.09
    aira
    0.07
    itution
    0.07
    627
    0.07
     meanings
    0.07
     bearing
    0.06
    agini
    0.06
     Meaning
    0.06
    awy
    0.06
    ocker
    0.06
    Activations Density 0.054%

    No Known Activations