© 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. 4656
    Prev
    Next
    INDEX
    Explanations

    phrases or references related to taxation and finance

    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
    ازÙħ
    -0.09
    itti
    -0.08
    вай
    -0.08
    ayıp
    -0.07
    湯
    -0.07
    anton
    -0.07
    CharacterSet
    -0.07
    ãĤĤãĤĬ
    -0.07
    /*č↵
    -0.07
    âķĿ
    -0.07
    POSITIVE LOGITS
    this
    0.08
     this
    0.08
     these
    0.07
    ses
    0.07
    such
    0.07
     such
    0.06
    these
    0.06
    singular
    0.06
    heit
    0.06
    0.06
    Activations Density 0.018%

    No Known Activations