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. 31-LLAMASCOPE-RES-131K
    6. 43986
    Prev
    Next
    INDEX
    Explanations

    references to art collections, exhibits, and inventory management

    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
    اÙĨÛĮ
    -0.07
    cek
    -0.06
    ç»ĥ
    -0.06
     jouer
    -0.06
    _EC
    -0.06
    radan
    -0.06
    _svg
    -0.06
    BCM
    -0.06
    CSR
    -0.06
    bjerg
    -0.06
    POSITIVE LOGITS
     archival
    0.13
     Archive
    0.12
     archive
    0.12
     Arch
    0.12
     archives
    0.11
    Archive
    0.11
     Archives
    0.11
     arch
    0.11
    archive
    0.10
    -archive
    0.10
    Activations Density 0.007%

    No Known Activations