© 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. 106202
    Prev
    Next
    INDEX
    Explanations

    references to tax payment processes and procedures

    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
    ãģ«ãģ¦
    -0.07
    ught
    -0.06
    stal
    -0.06
     Traverse
    -0.06
    ụn
    -0.06
    emo
    -0.06
    ix
    -0.06
    Util
    -0.06
    uminium
    -0.06
    oug
    -0.06
    POSITIVE LOGITS
     yours
    0.07
    íĥģ
    0.07
     GObject
    0.07
     æ®
    0.07
    .gs
    0.07
    .Dev
    0.06
     particulars
    0.06
    your
    0.06
    uez
    0.06
    rect
    0.06
    Activations Density 0.034%

    No Known Activations