© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 89974
    Prev
    Next
    INDEX
    Explanations

    references to debts or obligations in various contexts

    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
    oblin
    -0.07
    .Sdk
    -0.07
     ****************************************************************************
    -0.06
    ãĥĥãĤ¯
    -0.06
    mania
    -0.06
    adb
    -0.06
    amaha
    -0.06
    eya
    -0.06
    ÏĦή
    -0.06
    ocator
    -0.06
    POSITIVE LOGITS
    ãĥ£
    0.06
    eldom
    0.06
    aks
    0.06
    .ArgumentParser
    0.06
    udo
    0.06
    зв
    0.06
    ubo
    0.06
     Vul
    0.06
    nit
    0.06
    LIMIT
    0.06
    Activations Density 0.000%

    No Known Activations