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. 43845
    Prev
    Next
    INDEX
    Explanations

    terms related to food, particularly chocolate and its forms

    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
    :Event
    -0.06
    omik
    -0.06
    oodles
    -0.06
    "default
    -0.06
     acompanh
    -0.06
    à¸ģรรมà¸ģาร
    -0.06
     ìĤ¬ë¬´
    -0.06
     Å¡tÄĽ
    -0.06
    ÑĢÑĥÑĩ
    -0.06
    ledon
    -0.06
    POSITIVE LOGITS
     industry
    0.16
     genre
    0.15
     phenomenon
    0.14
     tradition
    0.13
     cra
    0.13
     paradigm
    0.13
     lifestyle
    0.13
     movement
    0.13
     concept
    0.12
     world
    0.12
    Activations Density 0.119%

    No Known Activations