© 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. 9-LLAMASCOPE-RES-131K
    11. 94801
    Prev
    Next
    INDEX
    Explanations

    references to institutional review and approval processes related to clinical trials

    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
    éĤ¦
    -0.09
    eum
    -0.07
    ków
    -0.07
    MLS
    -0.07
    GLfloat
    -0.07
    reature
    -0.07
    ÑĢÑıд
    -0.07
    igua
    -0.07
    oot
    -0.07
    ogy
    -0.07
    POSITIVE LOGITS
    atsapp
    0.06
     processes
    0.06
     yoksa
    0.06
    ches
    0.06
     Nah
    0.06
    469
    0.05
    671
    0.05
     for
    0.05
    _sink
    0.05
    oke
    0.05
    Activations Density 0.003%

    No Known Activations