© 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. 128870
    Prev
    Next
    INDEX
    Explanations

    phrases indicating discrepancies or differences in outcomes

    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
    566
    -0.06
     Sala
    -0.06
    aiser
    -0.06
    czy
    -0.06
    ades
    -0.06
     cre
    -0.06
     dangling
    -0.06
    оÑĤÑĢеб
    -0.06
    оÑģÑĤ
    -0.06
    sg
    -0.06
    POSITIVE LOGITS
    shadow
    0.07
    olson
    0.07
    achen
    0.07
    ساÙĨÛĮ
    0.07
    ãģ£ãģı
    0.07
    اساÙĨ
    0.07
    outu
    0.07
    iffs
    0.07
    ../../../../
    0.07
    phem
    0.07
    Activations Density 0.000%

    No Known Activations