© 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. 82237
    Prev
    Next
    INDEX
    Explanations

    references to music production and related elements

    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
    ignum
    -0.07
    rende
    -0.07
    rine
    -0.06
     filmer
    -0.06
    ledik
    -0.06
    askan
    -0.06
    UNET
    -0.06
    adge
    -0.06
     books
    -0.06
     DVDs
    -0.06
    POSITIVE LOGITS
     remix
    0.07
     Remix
    0.07
    track
    0.07
     track
    0.07
     pÅĻeb
    0.07
    -track
    0.07
    exclusive
    0.07
    浩
    0.07
     Club
    0.07
     Track
    0.07
    Activations Density 0.001%

    No Known Activations