© 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. 39094
    Prev
    Next
    INDEX
    Explanations

    phrases related to parks and their characteristics

    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
     BITTE
    -0.08
    outil
    -0.07
     ragaz
    -0.07
    äd
    -0.07
    wner
    -0.07
     meiden
    -0.07
    igner
    -0.07
     mädchen
    -0.07
    efon
    -0.07
    aiser
    -0.07
    POSITIVE LOGITS
     van
    0.11
    .nl
    0.09
    iteit
    0.09
     Een
    0.08
     voor
    0.08
    lij
    0.08
    ijn
    0.08
     op
    0.08
    uren
    0.08
     en
    0.07
    Activations Density 0.095%

    No Known Activations