© 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. 2579
    Prev
    Next
    INDEX
    Explanations

    commas and expressions of uncertainty or disarray

    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
    ugins
    -0.07
    лож
    -0.07
    letcher
    -0.07
    iero
    -0.06
    gaben
    -0.06
    outh
    -0.06
    bildung
    -0.06
    .nih
    -0.06
     جÙĨ
    -0.06
    SEA
    -0.06
    POSITIVE LOGITS
     depleted
    0.07
    åĿĤ
    0.06
    .openg
    0.06
    aggi
    0.06
     andre
    0.06
    raz
    0.06
     Ellison
    0.06
    .mit
    0.06
    ibu
    0.06
    ral
    0.06
    Activations Density 0.000%

    No Known Activations