© 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 EvalsExportsinterp-engineNEWAPI 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. 86654
    Prev
    Next
    INDEX
    Explanations

    terms related to social changes and cultural dynamics

    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
    asio
    -0.07
    aign
    -0.07
    cs
    -0.07
    inya
    -0.07
    оÑĢаз
    -0.07
    _predicate
    -0.06
     stuff
    -0.06
    ört
    -0.06
    &E
    -0.06
     åIJį
    -0.06
    POSITIVE LOGITS
     spaces
    0.07
     online
    0.07
     suction
    0.06
    }->
    0.06
     disc
    0.06
    /Peak
    0.06
     Disc
    0.06
     circulation
    0.06
    conomy
    0.06
    ulla
    0.06
    Activations Density 0.001%

    No Known Activations