© 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. 81983
    Prev
    Next
    INDEX
    Explanations

    personal expressions of feelings and sentiments

    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
    achel
    -0.08
    wdx
    -0.07
    поÑĢ
    -0.07
    emma
    -0.07
    леменÑĤ
    -0.07
    alars
    -0.06
    æĪĸèĢħ
    -0.06
     Carlson
    -0.06
    ÑĦи
    -0.06
     داÙĪ
    -0.06
    POSITIVE LOGITS
     Podle
    0.06
    stoi
    0.06
    ondo
    0.06
    rollo
    0.06
    roi
    0.06
     Sha
    0.06
     devel
    0.06
    yaw
    0.06
     moi
    0.06
    ½
    0.06
    Activations Density 0.026%

    No Known Activations