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. 96085
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships within scientific or statistical contexts

    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
     ChÃŃ
    -0.07
    illez
    -0.07
     Atatürk
    -0.07
    oÅĻ
    -0.07
    'http
    -0.07
    ovah
    -0.07
    ÑĮко
    -0.06
     dán
    -0.06
    VER
    -0.06
    eriod
    -0.06
    POSITIVE LOGITS
    alli
    0.07
    asty
    0.06
    coli
    0.06
     afl
    0.06
     Gh
    0.06
     unc
    0.06
     Bark
    0.06
     ante
    0.06
    anches
    0.06
     Gas
    0.06
    Activations Density 0.041%

    No Known Activations