© 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. 2573
    Prev
    Next
    INDEX
    Explanations

    key names or identifiers in legal or governmental contexts

    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
    udit
    -0.06
    .Selenium
    -0.06
    rolling
    -0.06
    UPLE
    -0.06
     áo
    -0.06
    _PH
    -0.06
    .car
    -0.06
    nge
    -0.06
     Episcopal
    -0.06
    itudes
    -0.06
    POSITIVE LOGITS
    odcast
    0.08
    ued
    0.07
    istor
    0.07
    eru
    0.07
    /legal
    0.07
    legal
    0.07
    abase
    0.07
     legal
    0.07
     Archae
    0.07
    upo
    0.06
    Activations Density 0.000%

    No Known Activations