© 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. 55297
    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
    .pixel
    -0.07
     samo
    -0.07
    ýt
    -0.06
    âĢĮâĢĮ
    -0.06
    Pic
    -0.06
     tez
    -0.06
    uger
    -0.06
    771
    -0.06
    /posts
    -0.06
    -uri
    -0.06
    POSITIVE LOGITS
     everybody
    0.08
     Everybody
    0.07
    SSION
    0.07
     ourselves
    0.07
     everyone
    0.07
    Everybody
    0.07
    everyone
    0.06
     unanimously
    0.06
    istributed
    0.06
    ingroup
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.