© 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. 22-LLAMASCOPE-RES-131K
    11. 3679
    Prev
    Next
    INDEX
    Explanations

    references to significant individuals and their accomplishments or death

    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
    εί
    -0.06
    Disallow
    -0.06
    orado
    -0.06
    ÑģÑĮко
    -0.06
    à¹Ħà¸ĭ
    -0.06
     thang
    -0.06
    ãĢģãĢģ
    -0.06
     عص
    -0.06
    _ioctl
    -0.06
    ÑģиÑĤ
    -0.06
    POSITIVE LOGITS
     death
    0.39
     died
    0.38
     deaths
    0.35
     dies
    0.31
    death
    0.31
    æŃ»
    0.30
     dying
    0.30
     dead
    0.30
     Death
    0.28
    -death
    0.28
    Activations Density 0.535%

    No Known Activations