© 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. 17-LLAMASCOPE-RES-131K
    11. 40847
    Prev
    Next
    INDEX
    Explanations

    historical references related to emperors and their monumental achievements

    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
    à¸ķะ
    -0.07
    ioni
    -0.07
    _HDR
    -0.07
    ewood
    -0.07
    coni
    -0.06
    Languages
    -0.06
    /release
    -0.06
     Oakland
    -0.06
    dere
    -0.06
    SF
    -0.06
    POSITIVE LOGITS
     Cele
    0.08
     Pac
    0.06
     Conf
    0.06
     prol
    0.06
     hs
    0.06
     Heaven
    0.06
     Mens
    0.06
    uzzi
    0.06
     Boat
    0.06
     Pills
    0.06
    Activations Density 0.017%

    No Known Activations