© 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. 22-LLAMASCOPE-RES-131K
    11. 4023
    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
    à¸ł
    -0.07
    ighet
    -0.07
    âh
    -0.06
     Cout
    -0.06
    ehler
    -0.06
    ylland
    -0.06
    å¢ĥ
    -0.06
    -esque
    -0.06
     [âĢ¦
    -0.06
    odor
    -0.06
    POSITIVE LOGITS
     Singapore
    0.08
    Singapore
    0.08
     Stra
    0.07
    okable
    0.07
     lah
    0.07
     Malaysian
    0.06
     Bent
    0.06
     nitel
    0.06
     criticisms
    0.06
    egie
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.