© 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. 57433
    Prev
    Next
    INDEX
    Explanations

    information related to celebrity net worth and personal details

    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
    irket
    -0.09
    аÑĢам
    -0.08
    oble
    -0.08
    _Connection
    -0.08
    antino
    -0.08
    اÙħÛĮÙĨ
    -0.07
    Introduced
    -0.07
    Enlarge
    -0.07
    $__
    -0.07
    ož
    -0.07
    POSITIVE LOGITS
    odo
    0.07
    ccb
    0.06
    w
    0.06
    age
    0.06
    adow
    0.05
     multim
    0.05
     Wrapped
    0.05
    class
    0.05
    {
    0.05
     eins
    0.05
    Activations Density 0.004%

    No Known Activations