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. 29-LLAMASCOPE-MLP-131K
    6. 5080
    Prev
    Next
    INDEX
    Explanations

    items and containers relevant to the transport and care of fish and aquariums

    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
    ¤í
    -0.07
    Owned
    -0.07
    anten
    -0.07
    /LICENSE
    -0.07
    zcze
    -0.06
     Owned
    -0.06
    -Owned
    -0.06
     ãĢľ
    -0.06
    unan
    -0.06
    orts
    -0.06
    POSITIVE LOGITS
    /py
    0.07
     lid
    0.07
     ju
    0.07
     lids
    0.07
    udas
    0.07
    sher
    0.07
    ptime
    0.07
    ache
    0.06
    arian
    0.06
     belle
    0.06
    Activations Density 0.035%

    No Known Activations