© 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. 125682
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial obligations and payments

    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
    리ìĬ¤
    -0.07
    ÄĽk
    -0.07
    apo
    -0.07
    ç©
    -0.07
    mdb
    -0.06
    erva
    -0.06
    ppv
    -0.06
    ẩu
    -0.06
    -navbar
    -0.06
     cust
    -0.06
    POSITIVE LOGITS
    strup
    0.07
    hind
    0.06
     lul
    0.06
     Kemp
    0.06
    ableOpacity
    0.06
     Ngh
    0.06
    ,strlen
    0.06
     Alma
    0.06
     tide
    0.06
    Datum
    0.06
    Activations Density 0.002%

    No Known Activations