© 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 EvalsExportsAPI 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. 106689
    Prev
    Next
    INDEX
    Explanations

    references to online surveys or reports regarding viewer behavior

    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
     mechan
    -0.06
     decade
    -0.06
    $MESS
    -0.06
    gratis
    -0.06
    бав
    -0.06
     decades
    -0.06
     Grat
    -0.06
    mae
    -0.06
    PerPixel
    -0.06
    íĮĮ
    -0.06
    POSITIVE LOGITS
    eler
    0.07
    emouth
    0.07
    jin
    0.06
    opup
    0.06
    enville
    0.06
     åľ¨çº¿
    0.06
     Swing
    0.06
    142
    0.06
    _SUR
    0.06
    brig
    0.06
    Activations Density 0.003%

    No Known Activations