Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-LLAMASCOPE-RES-131K
    6. 96041
    Prev
    Next
    INDEX
    Explanations

    specified formatting and structural elements within code or markup

    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
    ered
    -0.07
    BuilderInterface
    -0.06
    erable
    -0.06
    359
    -0.06
    lain
    -0.06
    úi
    -0.06
    lacak
    -0.06
    iec
    -0.06
    chartInstance
    -0.06
    68
    -0.06
    POSITIVE LOGITS
    ÑĢÑĸд
    0.07
     дÑĥÑĪ
    0.07
    寿
    0.07
    æ±Ĺ
    0.07
     ìĻĶ
    0.07
     عص
    0.07
     kanal
    0.07
    湯
    0.07
     porr
    0.07
    _consts
    0.07
    Activations Density 0.031%

    No Known Activations