© 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. 17-LLAMASCOPE-RES-131K
    6. 3763
    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
    æĤ
    -0.07
    iosa
    -0.06
    ISTA
    -0.06
    ieri
    -0.06
    toi
    -0.06
    orro
    -0.06
    uhl
    -0.06
     Yer
    -0.06
     &↵
    -0.06
     ÐĿаÑģеленнÑı
    -0.06
    POSITIVE LOGITS
    arrant
    0.07
    auer
    0.06
    ãĤıãģij
    0.06
    бÑĥÑĢг
    0.06
    _terminal
    0.06
     Aires
    0.06
    widgets
    0.06
    aling
    0.06
    bruar
    0.06
    rial
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.