© 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. 92643
    Prev
    Next
    INDEX
    Explanations

    key performance indicators or metrics related to view counts and statistics

    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
    urry
    -0.07
    oken
    -0.07
     Brew
    -0.06
    ymoon
    -0.06
     $('#'
    -0.06
     serialVersionUID
    -0.06
     Picker
    -0.06
    cedes
    -0.06
     Schwe
    -0.06
    ermann
    -0.06
    POSITIVE LOGITS
    antom
    0.07
    ylland
    0.07
     ant
    0.07
    CharArray
    0.06
    ););↵
    0.06
    SearchParams
    0.06
    bau
    0.06
    /backend
    0.06
    ublisher
    0.06
    ederland
    0.06
    Activations Density 0.001%

    No Known Activations