© 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. 107003
    Prev
    Next
    INDEX
    Explanations

    keywords related to common scenarios or setups in various contexts

    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
    ystick
    -0.07
    ister
    -0.07
    ibold
    -0.07
    egan
    -0.07
    wig
    -0.07
    zo
    -0.07
    ahn
    -0.07
    bjerg
    -0.07
    linger
    -0.06
    ISTER
    -0.06
    POSITIVE LOGITS
     fare
    0.09
    ä¹ĭä¸Ģ
    0.08
    /Common
    0.08
    /common
    0.07
     encountered
    0.07
     found
    0.07
    νά
    0.07
     ë§İìĿ´
    0.07
    à¸ŀà¸ļ
    0.07
     used
    0.07
    Activations Density 0.038%

    No Known Activations