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

    Neuronpedia

    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. 60395
    Prev
    Next
    INDEX
    Explanations

    terms related to financial charges and compliance costs

    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
     unt
    -0.06
     Bernstein
    -0.06
     Hollow
    -0.05
    [
    -0.05
    sp
    -0.05
    .
    -0.05
    ipse
    -0.05
    -t
    -0.05
     spo
    -0.05
    VP
    -0.05
    POSITIVE LOGITS
     Costs
    0.10
     costs
    0.10
    _COST
    0.09
    æĪIJæľ¬
    0.09
    covering
    0.09
     COST
    0.09
    _recovery
    0.09
    covers
    0.09
    ODB
    0.09
    _cost
    0.08
    Activations Density 0.020%

    No Known Activations