© 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. 77823
    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
     quirky
    -0.06
    zano
    -0.06
    OUCH
    -0.06
     quir
    -0.06
     è©ķ価
    -0.06
    íĨłíĨł
    -0.06
    abis
    -0.06
     Walsh
    -0.06
     ===>
    -0.06
    oter
    -0.06
    POSITIVE LOGITS
    exe
    0.07
    engl
    0.07
    efon
    0.06
    ä¸įäºĨ
    0.06
    asso
    0.06
     Cher
    0.06
    ett
    0.06
     fuck
    0.06
    uell
    0.06
    exo
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.