© 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. 15-LLAMASCOPE-RES-131K
    11. 87618
    Prev
    Next
    INDEX
    Explanations

    names and specific titles related to music and artistry

    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
    浩
    -0.07
    omik
    -0.07
    iesen
    -0.07
    lei
    -0.07
    abant
    -0.07
     Millions
    -0.07
    MainFrame
    -0.06
    SizeMode
    -0.06
    онов
    -0.06
    attern
    -0.06
    POSITIVE LOGITS
    åĻ¨
    0.07
     COPYING
    0.06
    urally
    0.06
    SION
    0.06
    house
    0.06
     genres
    0.06
     salon
    0.06
     VOC
    0.06
     Subscription
    0.06
     patrons
    0.06
    Activations Density 0.004%

    No Known Activations