© 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. 1616
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases related to time

    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
    ixmap
    -0.07
    haps
    -0.07
    fw
    -0.07
    swick
    -0.07
    IBC
    -0.07
    abble
    -0.07
    tiv
    -0.07
    elpers
    -0.07
    etto
    -0.06
    اÙĦس
    -0.06
    POSITIVE LOGITS
    aka
    0.08
    kili
    0.07
    EVER
    0.07
    amp
    0.06
    esa
    0.06
     gele
    0.06
    /forum
    0.06
    ampus
    0.06
    pawn
    0.06
    530
    0.06
    Activations Density 0.021%

    No Known Activations