© 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. 17-LLAMASCOPE-RES-131K
    11. 127126
    Prev
    Next
    INDEX
    Explanations

    references to specific nationalities and their contributions in various fields

    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
    fak
    -0.07
     fak
    -0.07
    smarty
    -0.07
    empl
    -0.06
    AXB
    -0.06
    utsch
    -0.06
    jang
    -0.06
    upert
    -0.06
    odos
    -0.06
    _pdata
    -0.06
    POSITIVE LOGITS
    iards
    0.08
    åį
    0.07
    279
    0.06
    azar
    0.06
     stub
    0.06
    ãģ£ãģį
    0.06
     addCriterion
    0.06
    ilan
    0.06
    lein
    0.06
    ROME
    0.06
    Activations Density 0.005%

    No Known Activations