© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 950
    Prev
    Next
    INDEX
    Explanations

    phrases related to food, particularly burgers and innovative cooking

    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
    ableView
    -0.08
    aldi
    -0.07
    ente
    -0.06
    anca
    -0.06
    ANTE
    -0.06
    uitable
    -0.06
    untime
    -0.06
    .Helper
    -0.06
     massaggi
    -0.06
    usable
    -0.06
    POSITIVE LOGITS
    oucher
    0.07
    /buttons
    0.07
    ãĥ¼ãĥĪ
    0.06
     Street
    0.06
     Bucket
    0.06
    ارات
    0.06
     bucket
    0.06
    loff
    0.06
     street
    0.06
    æ¤
    0.06
    Activations Density 0.017%

    No Known Activations