© 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. 15762
    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
    quares
    -0.08
    kins
    -0.07
    unders
    -0.06
    enced
    -0.06
    adoop
    -0.06
    è¿Ľä¸ĢæŃ¥
    -0.06
    ansa
    -0.06
    agnitude
    -0.05
     childs
    -0.05
     budd
    -0.05
    POSITIVE LOGITS
    gart
    0.07
     dword
    0.07
    adients
    0.07
    eel
    0.07
     licence
    0.06
     Serif
    0.06
    IFS
    0.06
     licences
    0.06
     Fowler
    0.06
     Morrow
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.