© 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. 40534
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to health and substance abuse

    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
    BaseContext
    -0.09
    gaard
    -0.08
     serialVersionUID
    -0.08
    ABCDEFGHIJKLMNOP
    -0.08
    aligned
    -0.07
    sein
    -0.07
    uluk
    -0.07
    sworth
    -0.07
    noDB
    -0.07
    slaught
    -0.07
    POSITIVE LOGITS
     Americans
    0.08
     tens
    0.07
     US
    0.07
     American
    0.07
    Americans
    0.06
     american
    0.06
     stat
    0.06
     consolid
    0.06
    ,
    0.06
     Exec
    0.06
    Activations Density 0.047%

    No Known Activations