© 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. 74465
    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
     amongst
    -0.06
    qv
    -0.06
     co
    -0.06
    iske
    -0.05
    uant
    -0.05
     Dirk
    -0.05
     connexion
    -0.05
    stra
    -0.05
    shal
    -0.05
    oli
    -0.05
    POSITIVE LOGITS
     COPYRIGHT
    0.08
     Poh
    0.07
    ุà¸ĩ
    0.07
    contents
    0.07
    ãĨį
    0.07
    spm
    0.07
    _accessible
    0.07
     Contents
    0.07
    kes
    0.07
    Âģ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.