© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1088
    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
    insn
    -0.07
    itsu
    -0.07
    ững
    -0.07
    èĬ¯
    -0.06
    ustos
    -0.06
    insi
    -0.06
     Xem
    -0.06
    EMBER
    -0.06
    tsy
    -0.06
    ery
    -0.06
    POSITIVE LOGITS
    ë°ĶìĿ´
    0.07
     eskort
    0.06
     Marion
    0.06
    _HT
    0.06
    jiang
    0.06
     instant
    0.06
     mile
    0.06
     bear
    0.06
    боÑĢ
    0.06
    iani
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.