© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59863
    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
     Ste
    -0.06
     ste
    -0.05
    âĦ¢
    -0.05
    -0.05
     parking
    -0.05
    łģ
    -0.05
     Meredith
    -0.05
     Xiao
    -0.05
    filtro
    -0.05
     Mon
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.10
    rün
    0.09
    eÅŁit
    0.08
     дво
    0.08
     nackte
    0.08
    аниÑĨ
    0.08
    deÅŁ
    0.08
    iyim
    0.08
     VÅ¡ech
    0.08
    BackingField
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.