© 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. 17-LLAMASCOPE-RES-131K
    11. 124137
    Prev
    Next
    INDEX
    Explanations

    terms related to repayment and financial obligations

    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
    maal
    -0.08
     repeating
    -0.08
    ialized
    -0.07
    /array
    -0.07
    ifice
    -0.07
     repetitive
    -0.07
    away
    -0.07
    erals
    -0.07
    kaar
    -0.07
     repetition
    -0.07
    POSITIVE LOGITS
    ments
    0.07
     exact
    0.07
    /rec
    0.07
    614
    0.07
    portion
    0.07
    ãĥ¼ãĥĸ
    0.07
    CursorPosition
    0.06
    able
    0.06
    nik
    0.06
     liá»ĩu
    0.06
    Activations Density 0.009%

    No Known Activations