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. 44081
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and mental health conditions

    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
    eway
    -0.06
    lenme
    -0.06
     Infant
    -0.06
    enheim
    -0.06
    ileo
    -0.06
     नर
    -0.06
    olon
    -0.06
    baby
    -0.06
    å©
    -0.05
    ÄĽr
    -0.05
    POSITIVE LOGITS
     com
    0.24
     co
    0.21
     concurrent
    0.14
     cof
    0.13
     con
    0.13
     coin
    0.12
    com
    0.12
     Com
    0.12
     Co
    0.11
     complic
    0.11
    Activations Density 0.023%

    No Known Activations