© 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. 82921
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial systems and banking activities

    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
     Flux
    -0.07
    moid
    -0.07
    elda
    -0.07
    éĺħ读次æķ°
    -0.06
     Debt
    -0.06
     Archive
    -0.06
    683
    -0.06
     kino
    -0.06
    vpn
    -0.06
    -generic
    -0.06
    POSITIVE LOGITS
     Recovery
    0.07
     recovery
    0.07
    ucz
    0.06
    oppel
    0.06
     limits
    0.06
    ysi
    0.06
     overnight
    0.06
     ФедеÑĢалÑĮ
    0.06
     depos
    0.06
    avit
    0.06
    Activations Density 0.009%

    No Known Activations