© 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. 2224
    Prev
    Next
    INDEX
    Explanations

    references to connections and relationships among people, places, and ancestry

    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
     Clarkson
    -0.07
    /Runtime
    -0.06
    urb
    -0.06
    cai
    -0.06
    ÙħÙĪد
    -0.06
    elay
    -0.06
     obed
    -0.06
    dür
    -0.06
    سة
    -0.06
    aring
    -0.06
    POSITIVE LOGITS
    ABCDEFGHIJKLMNOP
    0.08
    ixo
    0.07
    zsche
    0.07
    _via
    0.07
     Disconnect
    0.07
    /connect
    0.06
     reality
    0.06
     distant
    0.06
    heim
    0.06
    .decorators
    0.06
    Activations Density 0.021%

    No Known Activations