© 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. 82979
    Prev
    Next
    INDEX
    Explanations

    specific months and their corresponding numeric representations

    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
    fully
    -0.08
    argon
    -0.06
    ãĥ¬ãĤ¹
    -0.06
    ãĤ¹ãĥĿ
    -0.06
     Vul
    -0.06
    ful
    -0.06
    ÅĻiv
    -0.06
    ictim
    -0.06
     s
    -0.06
    ULO
    -0.06
    POSITIVE LOGITS
    adil
    0.07
    illet
    0.07
    ayar
    0.07
    ìľ¤
    0.06
    StreamWriter
    0.06
    Äĩi
    0.06
    iaux
    0.06
    awe
    0.06
     dirent
    0.06
    itzer
    0.06
    Activations Density 0.026%

    No Known Activations