© 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. 54298
    Prev
    Next
    INDEX
    Explanations

    the word "alle" and its variations 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
    tility
    -0.07
    rze
    -0.07
    owie
    -0.07
    dio
    -0.07
    eat
    -0.07
    ring
    -0.07
    vana
    -0.07
    rar
    -0.07
    RTC
    -0.07
    elem
    -0.06
    POSITIVE LOGITS
    maal
    0.09
    ally
    0.07
    oric
    0.07
    lo
    0.07
    agic
    0.06
    most
    0.06
    ÃŁen
    0.06
    ury
    0.06
    aves
    0.06
    اÙĦا
    0.06
    Activations Density 0.018%

    No Known Activations