© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129798
    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
    erness
    -0.07
    ulner
    -0.06
    arts
    -0.06
    rous
    -0.06
    áºŃn
    -0.06
    ares
    -0.06
    uestas
    -0.05
     flakes
    -0.05
    entes
    -0.05
     APR
    -0.05
    POSITIVE LOGITS
    ÑĢÑĥж
    0.07
    Aqu
    0.07
    ê¹
    0.06
    -transitional
    0.06
    .mas
    0.06
    GuidId
    0.06
    .Async
    0.06
    .navigateTo
    0.06
    .getMethod
    0.06
    _PROVID
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.