© 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. 73877
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and interactions with the IRS

    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
    à¥įà¤
    -0.07
    anou
    -0.07
    eson
    -0.06
    amp
    -0.06
    è´Ł
    -0.06
    ived
    -0.06
     cater
    -0.06
    ogg
    -0.06
    lal
    -0.06
    ertation
    -0.06
    POSITIVE LOGITS
    avÄĽ
    0.07
    Law
    0.07
     spun
    0.07
    ValueCollection
    0.06
     Innoc
    0.06
    iParam
    0.06
     advoc
    0.06
     localVar
    0.06
     prelim
    0.06
    .Undef
    0.06
    Activations Density 0.004%

    No Known Activations