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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39491
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the implementation of laws or regulations

    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
    ä¼
    -0.08
    éIJĺ
    -0.07
    们
    -0.06
    ÙĪÙĨÙĬ
    -0.06
    anio
    -0.06
    oleans
    -0.06
    ouv
    -0.06
    apr
    -0.06
    ราย
    -0.06
    orum
    -0.06
    POSITIVE LOGITS
     onDataChange
    0.07
    oS
    0.07
     immediately
    0.07
     immedi
    0.06
    ëĮĢë¡ľ
    0.06
    enaire
    0.06
    /use
    0.06
    inel
    0.06
    CppType
    0.06
    enty
    0.06
    Activations Density 0.006%

    No Known Activations