© 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. 27953
    Prev
    Next
    INDEX
    Explanations

    complex phrases that indicate obstacles, conditions, or requirements

    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
    ải
    -0.07
    ãģĨãģ¡
    -0.06
    oubted
    -0.06
    emark
    -0.06
    JR
    -0.06
    egra
    -0.06
    GES
    -0.06
    IGO
    -0.06
     various
    -0.06
     sou
    -0.06
    POSITIVE LOGITS
    adin
    0.07
     related
    0.07
    taire
    0.07
    ilight
    0.06
    alus
    0.06
     relacion
    0.06
     Herald
    0.06
     ÑģвÑıз
    0.06
    assel
    0.06
    ulus
    0.06
    Activations Density 0.038%

    No Known Activations