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. 22-LLAMASCOPE-RES-131K
    6. 5399
    Prev
    Next
    INDEX
    Explanations

    mentions of critical discussions or evaluations regarding Caribbean literature and its authors

    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
    ivé
    -0.06
    atten
    -0.06
    emente
    -0.06
    ؤ
    -0.06
    icari
    -0.06
    orthand
    -0.06
     ..
    -0.06
    ande
    -0.06
     surg
    -0.05
    pany
    -0.05
    POSITIVE LOGITS
    asaki
    0.07
    Ĭ
    0.07
    ...↵
    0.06
    usercontent
    0.06
    REA
    0.06
    κÏĮ
    0.06
    gart
    0.06
    nout
    0.06
    ffic
    0.06
    PACE
    0.06
    Activations Density 0.006%

    No Known Activations