© 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. 17-LLAMASCOPE-RES-131K
    11. 94040
    Prev
    Next
    INDEX
    Explanations

    numerical data related to individuals involved in accidents or incidents

    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
    .Xaml
    -0.08
    dio
    -0.07
    .openg
    -0.07
    ivor
    -0.07
    otos
    -0.07
    奪
    -0.07
    psc
    -0.07
    cie
    -0.07
    dit
    -0.07
    ιÏİ
    -0.06
    POSITIVE LOGITS
    enheim
    0.07
     address
    0.06
    .address
    0.06
     initials
    0.06
     ev
    0.06
    ">&#
    0.06
    åľ°åĿĢ
    0.06
     addresses
    0.06
    (address
    0.06
    _address
    0.05
    Activations Density 0.006%

    No Known Activations