© 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. 87475
    Prev
    Next
    INDEX
    Explanations

    code related to date and time manipulation in SQLite

    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
     Walsh
    -0.07
    >//
    -0.07
    hape
    -0.06
    AMENT
    -0.06
    terminal
    -0.06
    éĥ
    -0.06
    áº
    -0.06
    ESCO
    -0.06
     Sad
    -0.06
     ÄIJÆ°á»Ŀng
    -0.06
    POSITIVE LOGITS
    roj
    0.07
    mill
    0.07
    stell
    0.07
    .scalablytyped
    0.06
    nano
    0.06
     Mill
    0.06
    .gameserver
    0.06
    loff
    0.06
     Nan
    0.06
    è·Ŀ
    0.06
    Activations Density 0.024%

    No Known Activations