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. 11501
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical and emergency response situations

    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
    unix
    -0.07
    åĩºåĵģ
    -0.06
    unca
    -0.06
    ساÙħ
    -0.06
    urret
    -0.06
    รà¸ĵ
    -0.06
     moci
    -0.06
    ãģ
    -0.06
    lobby
    -0.06
     attractive
    -0.06
    POSITIVE LOGITS
     conducted
    0.09
     conducting
    0.08
     assigned
    0.08
     Conduct
    0.08
     conduct
    0.08
     Exercise
    0.07
     Aug
    0.07
     Feb
    0.07
     here
    0.07
     partnered
    0.07
    Activations Density 0.039%

    No Known Activations