© 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. 58269
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "parenting" and related concepts

    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
    aign
    -0.07
    üz
    -0.07
    orget
    -0.07
    ised
    -0.07
    icie
    -0.07
    celik
    -0.07
    issen
    -0.07
    ÅĻet
    -0.07
    idar
    -0.07
    /MIT
    -0.07
    POSITIVE LOGITS
    err
    0.07
    Styles
    0.06
     err
    0.06
     styles
    0.06
     style
    0.06
     Styles
    0.06
    enn
    0.06
    تا
    0.06
    337
    0.06
     sling
    0.06
    Activations Density 0.006%

    No Known Activations