© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 118319
    Prev
    Next
    INDEX
    Explanations

    terms related to tax deductions and charitable contributions

    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
    شتÙĩ
    -0.07
    finity
    -0.07
    ä»ĺãģij
    -0.06
     sat
    -0.06
    nome
    -0.06
    hta
    -0.06
     Agree
    -0.06
    Sat
    -0.06
    oken
    -0.06
    ington
    -0.06
    POSITIVE LOGITS
    ible
    0.07
    achable
    0.07
    IBLE
    0.06
    arme
    0.06
    'gc
    0.06
    /non
    0.06
     Vie
    0.06
    ucher
    0.06
    .Percent
    0.06
    swire
    0.06
    Activations Density 0.001%

    No Known Activations