© 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 EvalsExportsAPI 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. 130771
    Prev
    Next
    INDEX
    Explanations

    HTML or XML elements and their attributes

    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
     er
    -0.06
     rag
    -0.05
     ga
    -0.05
     g
    -0.05
    hip
    -0.05
     rather
    -0.05
     towards
    -0.05
     organ
    -0.05
     operation
    -0.05
     der
    -0.05
    POSITIVE LOGITS
    ForResource
    0.08
     VÅ¡ech
    0.07
    enu
    0.07
     meiden
    0.07
     searchBar
    0.07
    =search
    0.07
    ucene
    0.07
    _SEARCH
    0.07
    úsqueda
    0.07
    uni
    0.07
    Activations Density 0.000%

    No Known Activations