© 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. 62879
    Prev
    Next
    INDEX
    Explanations

    references to children and the experience of childhood

    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
    idth
    -0.07
    .Utilities
    -0.07
    ayer
    -0.07
    ihan
    -0.07
    ãĥĥ
    -0.07
    _UINT
    -0.06
    alat
    -0.06
    .Static
    -0.06
    .uni
    -0.06
    rouch
    -0.06
    POSITIVE LOGITS
    hood
    0.07
    ãĥ¼ãĥĹ
    0.06
    ENSOR
    0.06
    red
    0.06
    astr
    0.06
    UNCT
    0.06
    /Foundation
    0.05
    ANI
    0.05
    competitive
    0.05
    long
    0.05
    Activations Density 0.011%

    No Known Activations