© 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. 9-LLAMASCOPE-RES-131K
    11. 95051
    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
    ÑĢей
    -0.08
    xde
    -0.08
    datagrid
    -0.08
    asant
    -0.08
    .datab
    -0.07
    ãĢĤãĢĤ↵↵
    -0.07
    anche
    -0.07
    ARIANT
    -0.07
    efon
    -0.07
    canf
    -0.07
    POSITIVE LOGITS
     Courier
    0.06
    elle
    0.06
    in
    0.05
    çĪ½
    0.05
    oor
    0.05
    Numeric
    0.05
    uki
    0.05
     equipments
    0.05
    id
    0.05
     tall
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.