© 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. 15461
    Prev
    Next
    INDEX
    Explanations

    references to specific societies or organizations

    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
    eration
    -0.07
    _RATIO
    -0.07
    UBE
    -0.06
    åª
    -0.06
    омеÑĤ
    -0.06
    æ¯Ľ
    -0.06
    ps
    -0.06
    mant
    -0.06
    GENCY
    -0.06
    ÙĦس
    -0.06
    POSITIVE LOGITS
    ware
    0.07
    ze
    0.07
    ัà¸įà¸į
    0.06
    -wide
    0.06
    iedade
    0.06
    ãĥ³ãĤ¬
    0.06
    vice
    0.06
    wed
    0.06
    formance
    0.06
    (Of
    0.06
    Activations Density 0.009%

    No Known Activations