© 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. 17777
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "von" indicating a reference or attribution in context

    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
     the
    -0.07
    s
    -0.07
    ories
    -0.06
    -е
    -0.06
    ugi
    -0.06
     pornos
    -0.06
    flen
    -0.06
    ÙĩاÛĮ
    -0.06
    æĺ¯ä¸į
    -0.06
     Edison
    -0.06
    POSITIVE LOGITS
     allem
    0.07
    vek
    0.07
    etrofit
    0.07
    ankind
    0.07
    hm
    0.06
    awi
    0.06
    pt
    0.06
    .cut
    0.06
    findById
    0.06
    ãģĵãģĿ
    0.06
    Activations Density 0.020%

    No Known Activations