© 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. 18128
    Prev
    Next
    INDEX
    Explanations

    content related to school finance and education funding adjustments

    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
    åľ
    -0.07
    ripe
    -0.07
     regulation
    -0.06
    edia
    -0.06
    rame
    -0.06
    ruz
    -0.06
    reten
    -0.06
    llib
    -0.06
    ikip
    -0.06
    agra
    -0.06
    POSITIVE LOGITS
    ieder
    0.08
     formulas
    0.07
    jie
    0.07
     funding
    0.07
    acic
    0.07
    COPY
    0.07
    akis
    0.07
     Funding
    0.07
    patch
    0.07
     formula
    0.06
    Activations Density 0.007%

    No Known Activations