© 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. 85710
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    atto
    -0.06
    onz
    -0.06
    æ²ĸ
    -0.06
    uctose
    -0.06
    usu
    -0.06
    ideo
    -0.06
    dale
    -0.06
    elian
    -0.06
     Bucks
    -0.05
     dó
    -0.05
    POSITIVE LOGITS
    è°ĭ
    0.07
    تÙĩا
    0.07
    feld
    0.06
    etler
    0.06
    ãģĵãģ¡ãĤī
    0.06
     بس
    0.06
    indsight
    0.06
    λÏį
    0.06
    *)((
    0.06
    edb
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.