© 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. 130557
    Prev
    Next
    INDEX
    Explanations

    variations of the name "Moy" in different contexts

    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
    å¹ķ
    -0.07
    اÙĦØ©
    -0.06
    acemark
    -0.06
    ects
    -0.06
    inals
    -0.06
    ann
    -0.06
    asl
    -0.06
    uchs
    -0.06
     Transit
    -0.06
    coop
    -0.06
    POSITIVE LOGITS
    ambique
    0.09
    vement
    0.08
    ality
    0.08
    ammad
    0.07
    unted
    0.07
    roe
    0.07
    ILITY
    0.07
    ility
    0.07
    gomery
    0.07
    hammad
    0.07
    Activations Density 0.030%

    No Known Activations