© 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. 86004
    Prev
    Next
    INDEX
    Explanations

    phrases indicating missed opportunities or situations that are irreversible

    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
    lish
    -0.07
     timing
    -0.07
    CTL
    -0.06
    öyle
    -0.06
    ÅŁ
    -0.06
     Savage
    -0.06
    arih
    -0.06
    _padding
    -0.06
    aÅŁ
    -0.06
     Amerikan
    -0.06
    POSITIVE LOGITS
    kontakte
    0.07
    oux
    0.07
    ição
    0.07
    ród
    0.07
    olin
    0.07
    chyb
    0.06
    weeney
    0.06
    .UnitTesting
    0.06
    $LANG
    0.06
    eur
    0.06
    Activations Density 0.003%

    No Known Activations