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. 5651
    Prev
    Next
    INDEX
    Explanations

    active participatory phrases indicating current conditions or actions

    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
     now
    -0.13
     ÑĤепеÑĢÑĮ
    -0.12
     recently
    -0.11
    now
    -0.10
     recent
    -0.10
     soon
    -0.10
     previously
    -0.10
    çİ°åľ¨
    -0.10
     ahora
    -0.10
    recent
    -0.09
    POSITIVE LOGITS
     only
    0.10
    åıªèĥ½
    0.08
     ONLY
    0.08
     Only
    0.08
    queda
    0.08
     neither
    0.07
    alace
    0.07
    onz
    0.07
     mainly
    0.07
    only
    0.07
    Activations Density 0.066%

    No Known Activations