Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5502
    Prev
    Next
    INDEX
    Explanations

    instances of the word "play" and related phrases about music playback

    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
    amy
    -0.07
    osyal
    -0.07
     Rider
    -0.06
    thic
    -0.06
    pers
    -0.06
    UE
    -0.06
     Lamp
    -0.06
    stal
    -0.06
    cket
    -0.06
    UPI
    -0.06
    POSITIVE LOGITS
    backs
    0.08
    -back
    0.07
     Ñĩай
    0.07
     background
    0.06
    back
    0.06
    ÑĢак
    0.06
    izzo
    0.06
    Slim
    0.06
    background
    0.06
    loop
    0.06
    Activations Density 0.014%

    No Known Activations