© 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. 124487
    Prev
    Next
    INDEX
    Explanations

    zodiac-related terms and names

    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
    iÄĩ
    -0.07
    rac
    -0.07
    imbus
    -0.07
    tera
    -0.07
    íĴĪ
    -0.06
    ICIAL
    -0.06
    ipheral
    -0.06
    pendicular
    -0.06
    roz
    -0.06
    ÏĥμαÏĦα
    -0.06
    POSITIVE LOGITS
    /LICENSE
    0.07
    uhl
    0.07
    ereotype
    0.06
    MPI
    0.06
     overhead
    0.06
    /assert
    0.06
    вад
    0.06
     varargin
    0.06
     cop
    0.06
    .biz
    0.06
    Activations Density 0.003%

    No Known Activations