© 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. 75000
    Prev
    Next
    INDEX
    Explanations

    verbs denoting possession or occurrence, especially in different tenses

    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
     VÅ¡ech
    -0.07
     Danh
    -0.07
    ÙĪÙĨد
    -0.06
    yon
    -0.06
    _OID
    -0.06
     bel
    -0.06
    ysa
    -0.06
    /temp
    -0.06
    asel
    -0.06
     dara
    -0.06
    POSITIVE LOGITS
    tember
    0.08
    bour
    0.07
     itself
    0.07
    .Transactional
    0.07
    andler
    0.07
    upy
    0.07
    anje
    0.07
    ovit
    0.06
    oji
    0.06
    ória
    0.06
    Activations Density 0.059%

    No Known Activations