© 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. 56037
    Prev
    Next
    INDEX
    Explanations

    references to ideas, products, services, or entities related to design and business operations

    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
     kostenlose
    -0.07
     Kostenlose
    -0.07
     Loose
    -0.06
     smr
    -0.06
     loose
    -0.06
    é
    -0.06
     Sr
    -0.06
    ombok
    -0.06
     Liverpool
    -0.05
    /loose
    -0.05
    POSITIVE LOGITS
    apore
    0.08
    ruba
    0.07
    turnstile
    0.07
    acen
    0.07
    rung
    0.07
    .RequestMethod
    0.07
    otti
    0.07
    ector
    0.07
    Assignable
    0.07
    dealloc
    0.07
    Activations Density 0.018%

    No Known Activations