© 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. 2605
    Prev
    Next
    INDEX
    Explanations

    phrases that describe quantities and qualities related to demographics and attributes

    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
     Tide
    -0.07
    ÛĮد
    -0.06
    351
    -0.06
     Gors
    -0.06
    451
    -0.06
    yll
    -0.06
    eper
    -0.06
    ierce
    -0.06
    notated
    -0.06
    352
    -0.06
    POSITIVE LOGITS
    åĿĬ
    0.07
    /documentation
    0.07
    ald
    0.06
    gradable
    0.06
    olk
    0.06
    eger
    0.06
    BOARD
    0.06
    umba
    0.06
     sát
    0.06
    ngo
    0.06
    Activations Density 0.020%

    No Known Activations