© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 87411
    Prev
    Next
    INDEX
    Explanations

    instructions related to property assessments and inspections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    axter
    -0.06
     Janeiro
    -0.06
    aeper
    -0.06
    ptic
    -0.06
    duct
    -0.06
    RelativeTo
    -0.06
    artz
    -0.06
    ä¸Ģ
    -0.06
    theon
    -0.06
     Kop
    -0.06
    POSITIVE LOGITS
    /renderer
    0.08
    _ws
    0.08
    cü
    0.07
    žel
    0.07
     chung
    0.07
    RICS
    0.07
    าระ
    0.07
     Millet
    0.07
     MLS
    0.07
    .Extension
    0.07
    Activations Density 0.001%

    No Known Activations