© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 708
    Prev
    Next
    INDEX
    Explanations

    references to going above and beyond in efforts or actions

    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
     Seks
    -0.08
    arih
    -0.07
    ucht
    -0.07
    edral
    -0.06
    assen
    -0.06
     Zust
    -0.06
    /copyleft
    -0.06
     NONINFRINGEMENT
    -0.06
     Instruments
    -0.06
    losed
    -0.06
    POSITIVE LOGITS
    DEV
    0.07
    ä¸ĢæŃ¥
    0.07
     bent
    0.06
     beyond
    0.06
     dot
    0.06
    anje
    0.06
     extra
    0.06
    renders
    0.06
    iris
    0.06
    aurus
    0.06
    Activations Density 0.003%

    No Known Activations