© 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. 107306
    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
    eam
    -0.09
    ertino
    -0.08
    iez
    -0.07
    oller
    -0.07
    ESIS
    -0.07
    ["@
    -0.07
    วล
    -0.07
    agma
    -0.07
    igin
    -0.07
    ivil
    -0.07
    POSITIVE LOGITS
    ibble
    0.07
     vs
    0.07
    apphire
    0.06
     worldwide
    0.06
     mainly
    0.06
     manufacturing
    0.06
     mostly
    0.06
     yearly
    0.06
     globally
    0.06
     Chin
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.