© 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. 74970
    Prev
    Next
    INDEX
    Explanations

    terms related to the concepts of presence and expense, particularly in ethical or philosophical contexts

    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
    ilha
    -0.08
    rift
    -0.06
    olik
    -0.06
    èĬĿ
    -0.06
    iller
    -0.06
     fuse
    -0.06
    ohl
    -0.06
    ostel
    -0.05
    _Reference
    -0.05
    kir
    -0.05
    POSITIVE LOGITS
    yo
    0.07
    /by
    0.07
    uml
    0.07
    anmar
    0.07
    uming
    0.07
    795
    0.07
    vala
    0.07
    275
    0.07
    loi
    0.06
    sage
    0.06
    Activations Density 0.045%

    No Known Activations