© 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. 107956
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating relationships or 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
    indow
    -0.06
     typealias
    -0.06
     à¤īसन
    -0.06
    oc
    -0.06
     aconte
    -0.06
     ÏĢεÏģί
    -0.06
    FC
    -0.06
    uc
    -0.06
     omas
    -0.06
     occurrences
    -0.05
    POSITIVE LOGITS
    azaar
    0.08
    klä
    0.08
    immel
    0.07
     next
    0.07
    DMA
    0.07
    azar
    0.07
    aleb
    0.07
     Hari
    0.07
    heimer
    0.07
    mue
    0.07
    Activations Density 0.011%

    No Known Activations