© 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. 15-LLAMASCOPE-RES-131K
    11. 87017
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to data manipulation and operations

    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
    опол
    -0.08
    еÑģÑĮ
    -0.08
    оÑĢод
    -0.07
    ekil
    -0.07
    Ñİк
    -0.07
    å®Ŀ
    -0.07
     Morav
    -0.07
    /***************************************************************************↵
    -0.07
    ANTLR
    -0.07
    ercul
    -0.07
    POSITIVE LOGITS
     c
    0.06
    i
    0.06
     quot
    0.06
    all
    0.06
    ↵
    0.06
     ç¨
    0.05
     n
    0.05
    .
    0.05
     [
    0.05
    ums
    0.05
    Activations Density 0.009%

    No Known Activations