© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26757
    Prev
    Next
    INDEX
    Explanations

    references to applications and submissions related to various processes or events

    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
    bjerg
    -0.07
    OnInit
    -0.07
     Nam
    -0.07
    datagrid
    -0.07
     плаÑģÑĤи
    -0.07
    AMPL
    -0.07
    æŀĿ
    -0.06
    ONA
    -0.06
    oulouse
    -0.06
    à¸Ľà¸£à¸°à¸ģาศ
    -0.06
    POSITIVE LOGITS
     from
    0.08
     input
    0.06
     submissions
    0.06
     inputs
    0.06
    ukan
    0.06
    Forms
    0.06
     forms
    0.06
    æĿ¥èĩª
    0.06
    uliar
    0.06
     /*!<
    0.06
    Activations Density 0.167%

    No Known Activations