© 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. 56105
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a current point in time or stage

    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
    ÑĢик
    -0.07
    ÙģØ´
    -0.06
    quis
    -0.06
    abus
    -0.06
    ichtig
    -0.05
    venes
    -0.05
     mil
    -0.05
     Denn
    -0.05
     collect
    -0.05
    eca
    -0.05
    POSITIVE LOGITS
     momento
    0.10
     moment
    0.09
    moment
    0.08
     aktu
    0.07
     presently
    0.07
    olland
    0.07
    /moment
    0.07
    duce
    0.07
    碼
    0.07
    359
    0.07
    Activations Density 0.010%

    No Known Activations