© 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. 15-LLAMASCOPE-RES-131K
    11. 87841
    Prev
    Next
    INDEX
    Explanations

    terms related to legal procedures and regulatory compliance

    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
    enso
    -0.08
    anki
    -0.07
    ìĹŃ
    -0.07
    ÙĬار
    -0.07
    ä¿ĿéĻ©
    -0.07
    елов
    -0.06
     blamed
    -0.06
    ABA
    -0.06
    hub
    -0.06
    wicklung
    -0.06
    POSITIVE LOGITS
     property
    0.08
    ç·
    0.07
     Property
    0.07
     intervention
    0.07
     enforcement
    0.07
    herits
    0.07
    dek
    0.06
     spraying
    0.06
     dispos
    0.06
    éry
    0.06
    Activations Density 0.008%

    No Known Activations