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. 43641
    Prev
    Next
    INDEX
    Explanations

    terms related to blood cells and their role in health and disease

    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
    llum
    -0.07
    èĢ
    -0.07
    ombre
    -0.07
    ekim
    -0.06
    fen
    -0.06
     à¤ļà¤ķ
    -0.06
    ẩm
    -0.06
    icult
    -0.06
     workflows
    -0.06
    :"-"`↵
    -0.06
    POSITIVE LOGITS
     invaders
    0.18
     foreign
    0.18
     invading
    0.17
     pathogens
    0.15
    foreign
    0.15
     antig
    0.14
     foreigners
    0.14
     invaded
    0.13
     microbes
    0.12
     inv
    0.12
    Activations Density 0.016%

    No Known Activations