© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106870
    Prev
    Next
    INDEX
    Explanations

    content that relates to visual and multimedia elements, especially in the context of art and education

    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
    aucoup
    -0.07
    ürlich
    -0.07
    ertz
    -0.06
    à¹Ģย
    -0.06
    rganization
    -0.06
    ictionary
    -0.06
    hic
    -0.06
    .Ptr
    -0.06
    getApplication
    -0.06
     Relief
    -0.06
    POSITIVE LOGITS
    OCKET
    0.07
    ancer
    0.07
    swire
    0.06
    ScrollIndicator
    0.06
    κηÏĤ
    0.06
    quin
    0.06
    senal
    0.06
    оÑī
    0.06
    .scalablytyped
    0.06
    ัà¸Ļà¸Ń
    0.06
    Activations Density 0.091%

    No Known Activations