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. MLP Out
    5. 25-LLAMASCOPE-MLP-131K
    6. 72617
    Prev
    Next
    INDEX
    Explanations

    references to scientific research and studies

    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
    iamond
    -0.06
    igua
    -0.06
    ếp
    -0.06
    rawler
    -0.06
    tee
    -0.06
    微软éĽħé»ij
    -0.06
    æ°§
    -0.06
     Gst
    -0.05
    unity
    -0.05
     powers
    -0.05
    POSITIVE LOGITS
     Twe
    0.07
    zos
    0.07
    ZO
    0.07
    chter
    0.07
    DED
    0.07
    aus
    0.06
    plevel
    0.06
    DDD
    0.06
    vsp
    0.06
    دÛĮگر
    0.06
    Activations Density 0.001%

    No Known Activations