© 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. 93541
    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
     Conv
    -0.06
    /storage
    -0.06
    993
    -0.06
    ador
    -0.06
    ::__
    -0.06
     Gamb
    -0.05
     Enrique
    -0.05
     Yug
    -0.05
    eah
    -0.05
    رÙĪز
    -0.05
    POSITIVE LOGITS
    elage
    0.06
    GRAM
    0.06
    LING
    0.06
    iesel
    0.06
    issance
    0.06
    villa
    0.06
    dcc
    0.06
    å¦
    0.06
    azen
    0.06
    adc
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.