© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93668
    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
     "
    -0.07
     Jain
    -0.07
     ("
    -0.06
     &
    -0.06
     overall
    -0.06
    olan
    -0.06
     (
    -0.06
     [
    -0.06
    ienes
    -0.06
     Pa
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.09
    大åħ¨
    0.07
    BorderStyle
    0.07
     územ
    0.07
     cÄĥn
    0.07
    .::
    0.07
    AtA
    0.07
    InParameter
    0.07
     CharSet
    0.07
    istence
    0.07
    Activations Density 0.003%

    No Known Activations