© 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. 70432
    Prev
    Next
    INDEX
    Explanations

    numerical data related to population statistics and health effects

    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
    åĭ¤
    -0.07
    _flg
    -0.07
    ắng
    -0.07
    usan
    -0.06
    æ°
    -0.06
    ả
    -0.06
    Ø´Ùħ
    -0.06
    /effects
    -0.06
    –↵↵
    -0.06
    enstein
    -0.06
    POSITIVE LOGITS
    itre
    0.07
    ummer
    0.07
     ordering
    0.07
     conc
    0.06
     Hughes
    0.06
    è¼
    0.06
    downloads
    0.06
    572
    0.06
    epad
    0.06
    //{{
    0.06
    Activations Density 0.002%

    No Known Activations