© 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. 106242
    Prev
    Next
    INDEX
    Explanations

    inquiries and considerations about property and emergency preparedness

    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
    anos
    -0.07
    ollen
    -0.07
    ivot
    -0.06
    /global
    -0.06
     ElementType
    -0.06
     FactoryBot
    -0.06
    oola
    -0.06
    sth
    -0.06
    ICES
    -0.06
    utters
    -0.06
    POSITIVE LOGITS
     deal
    0.07
     Deal
    0.07
     acquire
    0.07
     Acquisition
    0.07
     acquisition
    0.06
     USDA
    0.06
     sécur
    0.06
    exit
    0.06
    EXIT
    0.06
     JV
    0.06
    Activations Density 0.002%

    No Known Activations