© 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. 16416
    Prev
    Next
    INDEX
    Explanations

    references to students, children, employees, and people within various contexts of social or community engagement

    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
    öz
    -0.07
    oric
    -0.06
    stery
    -0.06
    ossip
    -0.06
    ularity
    -0.06
    beros
    -0.06
     går
    -0.06
    aber
    -0.06
    urgence
    -0.06
    ableView
    -0.06
    POSITIVE LOGITS
    arden
    0.07
     should
    0.07
     же
    0.07
     needs
    0.06
     ç±
    0.06
    izr
    0.06
     shouldn
    0.06
    alth
    0.06
     ÙħطاÙĦ
    0.06
    ucci
    0.06
    Activations Density 0.029%

    No Known Activations