© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124918
    Prev
    Next
    INDEX
    Explanations

    content related to personal growth and self-improvement

    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
    rite
    -0.06
    outu
    -0.06
    ä¹ī
    -0.06
     irre
    -0.06
    URT
    -0.06
     pass
    -0.06
    habi
    -0.06
     Diabetes
    -0.06
    iges
    -0.06
    義
    -0.06
    POSITIVE LOGITS
     Seks
    0.07
    çīĮ
    0.07
    æk
    0.07
     Brom
    0.07
    é»İ
    0.06
    .tp
    0.06
    celik
    0.06
    .bt
    0.06
    ((((
    0.06
    inent
    0.06
    Activations Density 0.021%

    No Known Activations