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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16674
    Prev
    Next
    INDEX
    Explanations

    keywords and names associated with specific individuals and events, particularly in a political or sports context

    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
    ç´Ģ
    -0.07
    ź
    -0.06
    umm
    -0.06
    оÑĢалÑĮ
    -0.06
     Cush
    -0.06
    abbo
    -0.06
    èĭ
    -0.06
    "<?
    -0.06
    /stream
    -0.06
     обÑĭ
    -0.06
    POSITIVE LOGITS
     Bulgarian
    0.13
     Bulgaria
    0.13
     Sofia
    0.12
     Bulg
    0.09
     Telerik
    0.09
    elerik
    0.09
     Dimit
    0.08
     بÙĦغ
    0.08
     Burg
    0.08
     bul
    0.07
    Activations Density 0.024%

    No Known Activations