© 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. 85712
    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
     пÑĢием
    -0.06
    726
    -0.06
    dued
    -0.06
    ilyn
    -0.06
    اعÙĬ
    -0.06
    eneg
    -0.06
    rought
    -0.06
    721
    -0.06
    inci
    -0.06
     sat
    -0.05
    POSITIVE LOGITS
    asma
    0.07
     compens
    0.07
    AVIS
    0.07
     Insight
    0.07
    ityEngine
    0.07
     Flem
    0.07
    okit
    0.07
    urement
    0.06
     muschi
    0.06
     insights
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.