© 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. 15499
    Prev
    Next
    INDEX
    Explanations

    expressions of desire and possession

    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
    ãĥį
    -0.06
    inder
    -0.06
     NSStringFromClass
    -0.06
    hausen
    -0.06
    eec
    -0.06
    vil
    -0.06
     Seam
    -0.06
    _locator
    -0.06
    indi
    -0.06
     thÃłnh
    -0.06
    POSITIVE LOGITS
     purchase
    0.07
    кÑĥп
    0.06
    QUIRE
    0.06
    ãĤıãģij
    0.06
    pdb
    0.06
    iva
    0.06
     Ñģебе
    0.05
    bis
    0.05
    ISTRIBUT
    0.05
    ORD
    0.05
    Activations Density 0.015%

    No Known Activations