© 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. 124629
    Prev
    Next
    INDEX
    Explanations

    financial obligations and debts related to loans and mortgages

    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
    roys
    -0.06
    elere
    -0.06
     Erect
    -0.06
    Æ¡m
    -0.06
    leta
    -0.06
    çu
    -0.06
    kv
    -0.06
    سÙĦ
    -0.06
    лиÑĪком
    -0.06
     вв
    -0.06
    POSITIVE LOGITS
    rap
    0.06
     Equity
    0.06
    ambi
    0.06
     refin
    0.06
     mort
    0.06
     ownership
    0.06
     Ownership
    0.06
    æĬµ
    0.06
    Ownership
    0.06
     finish
    0.05
    Activations Density 0.007%

    No Known Activations