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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 96223
    Prev
    Next
    INDEX
    Explanations

    data types related to strings and numbers in programming 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
    edBy
    -0.07
    bek
    -0.07
    nun
    -0.07
    edla
    -0.07
     ung
    -0.07
    tru
    -0.06
    bourne
    -0.06
    bourg
    -0.06
    tu
    -0.06
     ogl
    -0.06
    POSITIVE LOGITS
    igon
    0.07
    [^
    0.06
     pro
    0.06
    imals
    0.06
    ìĭł
    0.06
    rych
    0.06
    ves
    0.06
    outh
    0.06
    acente
    0.06
     \/
    0.06
    Activations Density 0.003%

    No Known Activations