© 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. 87487
    Prev
    Next
    INDEX
    Explanations

    details related to event pricing and admission fees

    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
    osp
    -0.06
    fore
    -0.06
    asket
    -0.06
    lion
    -0.06
    edom
    -0.06
    bourg
    -0.06
    udder
    -0.06
    .gf
    -0.06
    pd
    -0.06
     object
    -0.06
    POSITIVE LOGITS
    (children
    0.07
    åŃIJä¾Ľ
    0.07
     children
    0.07
     Children
    0.06
    children
    0.06
    âĸį
    0.06
    -notes
    0.06
     Gratuit
    0.06
    ,void
    0.06
    Children
    0.06
    Activations Density 0.004%

    No Known Activations